© 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. 106922
    Prev
    Next
    INDEX
    Explanations

    code

    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
    beits
    -0.25
     Lauderdale
    -0.25
    :"-
    -0.24
    redentials
    -0.24
    REDENTIAL
    -0.24
    å®ļ
    -0.24
    .instant
    -0.24
    çĨĬ
    -0.24
    ä¿¡
    -0.23
    atoon
    -0.23
    POSITIVE LOGITS
    åıijåŀĭ
    0.25
    ç´§åĩij
    0.25
    dfd
    0.24
    æµģåIJij
    0.24
     TypeName
    0.24
    getOption
    0.24
    lav
    0.24
    åıįè¿ĩæĿ¥
    0.23
    èĥģ
    0.23
    IDD
    0.23
    Activations Density 6.989%

    No Known Activations