© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Qwen2.5-7B-IT
    7. Resid Post - 131k
    9. 15-RESID-POST-AA
    11. 44899
    Prev
    Next
    INDEX
    Explanations

    skip

    np_max-act · gemini-2.0-flash

    compound technical terms and concatenated identifiers (including CamelCase and fused multiword nouns, often with -ing endings).

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    𝕙
    -0.07
     Convenient
    -0.07
     stu
    -0.07
     Advent
    -0.07
    -Cs
    -0.07
     compelled
    -0.07
     Narrow
    -0.07
    ierce
    -0.07
     fuller
    -0.06
     deserving
    -0.06
    POSITIVE LOGITS
    ToArray
    0.08
    endregion
    0.07
     ülkem
    0.07
    התא
    0.07
     productions
    0.07
     меропри
    0.07
     PROGMEM
    0.07
    strtotime
    0.07
    Porno
    0.07
     المناطق
    0.07
    Activations Density 1.713%

    No Known Activations