© 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. 130255
    Prev
    Next
    INDEX
    Explanations

    beginnings/endings

    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
    åĬĽ
    -0.28
    åĴĮå°ļ
    -0.27
     MISSING
    -0.27
    .setColumns
    -0.26
    æĪIJ为ä¸ŃåĽ½
    -0.25
    轨迹
    -0.25
    ä¸ŃåĽ½éĺŁ
    -0.25
    éĻ¤å¤ĸ
    -0.25
    yms
    -0.25
    ersen
    -0.25
    POSITIVE LOGITS
     summer
    0.62
     winter
    0.60
     autumn
    0.59
     season
    0.59
    ç§ĭåŃ£
    0.57
    ç§ĭåĨ¬
    0.56
    ç§ĭ天
    0.56
    ç§ĭ
    0.56
     holiday
    0.54
     Season
    0.54
    Activations Density 0.024%

    No Known Activations