© 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. 22-TRANSCODER-HP
    7. 99281
    Prev
    Next
    INDEX
    Explanations

    so

    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
    Negative Logits
     Economist
    -0.28
    mour
    -0.27
    ä¿¡ç®±
    -0.26
    çľļ
    -0.26
    ambi
    -0.25
    åĽº
    -0.25
    ç§ģ人
    -0.24
    iones
    -0.24
    ç¡®å®ŀæĺ¯
    -0.24
    plode
    -0.24
    POSITIVE LOGITS
     now
    0.28
    åľ¨è¿ĩ渡
    0.26
    _geom
    0.26
     irr
    0.25
    ival
    0.25
    ä»Ħ
    0.25
     tomorrow
    0.24
     student
    0.24
     ÑĪколÑĮ
    0.24
     pot
    0.24
    Activations Density 0.015%

    No Known Activations