© 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. 149157
    Prev
    Next
    INDEX
    Explanations

    Code, gibberish, and symbols

    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
     lore
    -0.29
    getPost
    -0.27
    ment
    -0.26
    poster
    -0.25
     Poster
    -0.25
    (TM
    -0.25
    fbe
    -0.24
    ldre
    -0.24
    ç¼£
    -0.24
     yal
    -0.24
    POSITIVE LOGITS
    åIJĬ
    0.28
    亲
    0.28
    elli
    0.28
    åįģåŃĹ
    0.27
    CDATA
    0.25
    èľ»
    0.24
    åħĪéĶĭ
    0.24
    尾巴
    0.24
    ç»ĵå°¾
    0.24
    nuts
    0.23
    Activations Density 0.168%

    No Known Activations