© 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. 7-RESID-POST-AA
    11. 102905
    Prev
    Next
    INDEX
    Explanations

    Observing a process

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    �
    -0.08
    打进
    -0.07
    してください
    -0.07
     Highland
    -0.06
    /job
    -0.06
     nhỏ
    -0.06
     Michigan
    -0.06
     Forum
    -0.06
     shitty
    -0.06
    海盗
    -0.06
    POSITIVE LOGITS
     hombre
    0.07
    éné
    0.07
    אנחנו
    0.07
    ("//*[@
    0.07
     المناسب
    0.07
     cath
    0.06
    extérieur
    0.06
    历史
    0.06
     Eph
    0.06
     Kens
    0.06
    Activations Density 0.256%

    No Known Activations