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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 130164
    Prev
    Next
    INDEX
    Explanations

    change

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     reforms
    -0.26
    tant
    -0.24
    issa
    -0.24
    éļı
    -0.24
     correspondent
    -0.24
    esan
    -0.24
     embroidered
    -0.23
    ::-
    -0.23
     spun
    -0.23
    ä½ĵåĪ¶æĶ¹éĿ©
    -0.23
    POSITIVE LOGITS
    trys
    0.27
    大åѦ
    0.25
    ç°ª
    0.25
    æīĢæľīçļĦ
    0.24
    anoia
    0.24
    åIJİå¤ĩ
    0.23
     colleges
    0.23
    ÑĨев
    0.23
    ä¸ī家
    0.23
    åŃ
    0.22
    Activations Density 0.011%

    No Known Activations