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. 24175
    Prev
    Next
    INDEX
    Explanations

    {

    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
     открыва
    -0.07
    人参
    -0.07
    _GPIO
    -0.07
    änner
    -0.07
    .DTO
    -0.07
    大会上
    -0.07
     орг
    -0.07
    官司
    -0.07
     натур
    -0.07
    컵
    -0.07
    POSITIVE LOGITS
    );\
    0.08
    喜好
    0.07
     importante
    0.06
    ');↵
    0.06
    ]');↵
    0.06
    osphate
    0.06
    ]';↵
    0.06
     Elijah
    0.06
    "]↵↵
    0.06
     //↵
    0.06
    Activations Density 0.004%

    No Known Activations