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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 2977
    Prev
    Next
    INDEX
    Explanations

    wards

    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
     Evangel
    -0.06
    origin
    -0.06
    ãn
    -0.06
    ng
    -0.06
     représ
    -0.06
    кор
    -0.06
     Peggy
    -0.06
     Colleg
    -0.06
    orf
    -0.06
    unix
    -0.06
    POSITIVE LOGITS
    flutter
    0.08
     payload
    0.08
     <--
    0.08
    |--
    0.07
    =====
    0.07
    .tmp
    0.07
    叠加
    0.07
    一部
    0.07
    .reset
    0.07
    ponsible
    0.07
    Activations Density 0.005%

    No Known Activations