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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Qwen2.5-7B-IT
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 68985
    Prev
    Next
    INDEX
    Explanations

    Code/mathematics context

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-qwen2.5-7b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Overview
    -0.07
     Kosovo
    -0.07
     ve
    -0.07
    捋
    -0.07
     ki
    -0.07
    ียน
    -0.07
     Ladies
    -0.07
    癫
    -0.07
    ón
    -0.06
    提拔
    -0.06
    POSITIVE LOGITS
    water
    0.08
    picable
    0.07
    ᠮ
    0.07
    salary
    0.07
    🏚
    0.07
    PHP
    0.07
     stencil
    0.07
    _BOTTOM
    0.07
    ,sizeof
    0.06
     الإنترنت
    0.06
    Activations Density 0.022%

    No Known Activations