© 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. 24-TRANSCODER-HP
    7. 151229
    Prev
    Next
    INDEX
    Explanations

    Location descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    ä½Ĩæĺ¯å¦Ĥæŀľ
    -0.27
    zers
    -0.27
    бÑĥÑĢ
    -0.26
    åĪĩæĸŃ
    -0.26
    orian
    -0.25
    chron
    -0.25
    åľ¨è¿ĩ渡
    -0.25
    ç»ı纪人
    -0.24
    ĴĮ
    -0.23
    ä½Ĩæĺ¯å¯¹äºİ
    -0.23
    POSITIVE LOGITS
    TM
    0.29
     Exist
    0.26
    B
    0.25
    G
    0.24
    “
    0.24
    inh
    0.24
    åŃĺåľ¨
    0.23
    Round
    0.23
    fw
    0.23
     Module
    0.23
    Activations Density 0.359%

    No Known Activations