© 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. 151240
    Prev
    Next
    INDEX
    Explanations

    code, technical jargon

    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
    çļĦè¯Ŀ
    -0.30
    ,
    -0.29
     is
    -0.27
    2
    -0.27
    çļĦæĥħåĨµä¸ĭ
    -0.27
     *
    -0.27
    ons
    -0.26
    antic
    -0.26
     so
    -0.25
     tu
    -0.25
    POSITIVE LOGITS
    semb
    0.32
    mares
    0.30
    åIJį家
    0.29
    rary
    0.29
    ç¯ĩæĸĩç«ł
    0.28
    èĨ¨
    0.26
    ç¯ĩç«ł
    0.26
     Trafford
    0.26
     Ceramic
    0.25
    (Collection
    0.24
    Activations Density 0.024%

    No Known Activations