© 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. 98293
    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
    wed
    -0.26
    éĢģåĩº
    -0.26
    zell
    -0.26
    ç»ıèIJ¥æ¨¡å¼ı
    -0.26
    uja
    -0.25
    è¿ĻäºĽéĹ®é¢ĺ
    -0.25
    è¿ĻäºĽéĥ½æĺ¯
    -0.25
     Sew
    -0.25
    åĪ°æľĢåIJİ
    -0.24
    ä¸įçĶ¨æĭħå¿ĥ
    -0.24
    POSITIVE LOGITS
    è´µ
    0.30
     familiar
    0.27
    çĨŁæĤī
    0.25
    oÄŁ
    0.25
    èĩ³å°ij
    0.25
    çĨŁæĤīçļĦ
    0.25
    leo
    0.25
     acquainted
    0.24
    breaking
    0.24
    brates
    0.24
    Activations Density 0.001%

    No Known Activations