© 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. 23-TRANSCODER-HP
    7. 25390
    Prev
    Next
    INDEX
    Explanations

    number

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    roe
    -0.28
    wg
    -0.26
     sidl
    -0.25
    uÅŁ
    -0.25
     trá»įng
    -0.25
    rollers
    -0.25
    åıĮéĩį
    -0.25
    ."_
    -0.24
    itzer
    -0.24
    ä¸įä¼ļåĨį
    -0.24
    POSITIVE LOGITS
    çŃ¾çº¦
    0.26
    okit
    0.25
    模å¼ı
    0.25
    FLT
    0.25
    åĪ¶çº¦
    0.24
    çĽijæĬ¤
    0.24
    ga
    0.24
    ensor
    0.24
    æĢ¥æĢ§
    0.24
    头éĥ¨
    0.23
    Activations Density 0.004%

    No Known Activations