© 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. 87917
    Prev
    Next
    INDEX
    Explanations

    Appear

    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
    ä¸įçIJĨ
    -0.31
    DataContract
    -0.28
    yclopedia
    -0.28
    -guard
    -0.28
    егод
    -0.26
    quila
    -0.25
     ****************************************************************************
    -0.25
     guarded
    -0.25
    {*
    -0.25
    -mile
    -0.25
    POSITIVE LOGITS
     perceived
    0.57
     apparent
    0.56
    çľĭä¼¼
    0.56
     pretended
    0.48
     seeming
    0.48
    çľĭèµ·æĿ¥
    0.47
     perception
    0.45
    ä¼¼ä¹İæĺ¯
    0.44
     illusion
    0.44
     pretend
    0.43
    Activations Density 0.012%

    No Known Activations