© 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. 20-TRANSCODER-HP
    7. 140868
    Prev
    Next
    INDEX
    Explanations

    island

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_20.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.20.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    estate
    -0.27
    è¿ĩ渡
    -0.26
    èļģ
    -0.26
    æĿİåħĪçĶŁ
    -0.26
    .codehaus
    -0.25
    omon
    -0.25
    achable
    -0.24
    æĺł
    -0.24
    emble
    -0.24
    两项
    -0.24
    POSITIVE LOGITS
     pellet
    0.26
    ions
    0.26
     Pel
    0.26
    PMC
    0.25
    qing
    0.25
    psc
    0.25
    uten
    0.24
    CPP
    0.24
    ypress
    0.24
    ç¢Į
    0.23
    Activations Density 42.215%

    No Known Activations