© 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. 88254
    Prev
    Next
    INDEX
    Explanations

    This

    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
    SV
    -0.29
     SV
    -0.29
    ç»ĵå±Ģ
    -0.28
    -TV
    -0.27
    æĿIJè´¨
    -0.27
     eup
    -0.26
     (!_
    -0.25
    éŁ³
    -0.24
    大使
    -0.24
    ACEMENT
    -0.23
    POSITIVE LOGITS
     research
    0.27
    tring
    0.25
    ordination
    0.25
    ä¸İä¼Ĺä¸įåIJĮ
    0.25
     particulière
    0.24
    ("{
    0.24
     Japan
    0.23
    ('{
    0.23
    KEN
    0.23
    è¿ĺ好
    0.23
    Activations Density 0.001%

    No Known Activations