Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 109848
    Prev
    Next
    INDEX
    Explanations

    named

    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
     infinite
    -0.06
     Пер
    -0.06
     insecure
    -0.06
     extrem
    -0.06
    יפות
    -0.06
     verz
    -0.06
    انون
    -0.06
    (year
    -0.06
    等地
    -0.06
    atio
    -0.06
    POSITIVE LOGITS
     пользу
    0.07
     Fulton
    0.07
    大发
    0.07
    折扣
    0.07
     cameras
    0.06
     COMMON
    0.06
     boa
    0.06
    🐯
    0.06
     hạ
    0.06
     Emit
    0.06
    Activations Density 0.010%

    No Known Activations