© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 142740
    Prev
    Next
    INDEX
    Explanations

    resistance

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    lando
    -0.28
    ç²īç¢İ
    -0.27
    éģŃéģĩ
    -0.26
    ä¹ī
    -0.26
     decad
    -0.25
    çļĦç»ıåİĨ
    -0.25
    çļĦçĥŃæĥħ
    -0.24
     thức
    -0.24
    çŃīåIJĦç§į
    -0.24
    çļĦ积æŀģæĢ§
    -0.24
    POSITIVE LOGITS
     Tow
    0.30
    箪
    0.29
    ìĻķ
    0.23
    èľĥ
    0.23
    oub
    0.23
    รà¸ĩ
    0.23
    åħļåĴĮ
    0.23
     law
    0.23
     Redistributions
    0.23
    è°Ĺ
    0.23
    Activations Density 7.207%

    No Known Activations