© 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. 87882
    Prev
    Next
    INDEX
    Explanations

    .

    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
    ï¼ļ<
    -0.30
    æľªå¿ħ
    -0.29
    iali
    -0.28
     remembering
    -0.27
    /desktop
    -0.26
    éŀį
    -0.26
    赶æĿ¥
    -0.26
     Kot
    -0.26
     transports
    -0.25
    esk
    -0.25
    POSITIVE LOGITS
    To
    0.29
     To
    0.29
    ,
    0.25
    gen
    0.25
    Ex
    0.25
    Pro
    0.25
     $(
    0.25
    Chain
    0.25
    bas
    0.25
    ÑĨе
    0.25
    Activations Density 0.001%

    No Known Activations