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

    Neuronpedia

    Jacobian LensNEW
    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. 43823
    Prev
    Next
    INDEX
    Explanations

    Commit messages

    np_max-act · gemini-2.0-flash

    machine-generated technical metadata and identifiers—hex/hash chunks, GUID or commit ID segments, and version/date numerals.

    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
    ⁂
    -0.07
    𬶋
    -0.07
    🔎
    -0.07
    italic
    -0.07
    מסעדה
    -0.07
    ⏪
    -0.07
    figcaption
    -0.06
    wc
    -0.06
    _alt
    -0.06
    🏖
    -0.06
    POSITIVE LOGITS
     government
    0.07
    売
    0.07
     GeForce
    0.07
    ปกครอง
    0.07
     temperature
    0.07
    ヽ
    0.07
     getenv
    0.07
     dumps
    0.07
     GENER
    0.07
    人人
    0.07
    Activations Density 0.882%

    No Known Activations