© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 20-TRANSCODER-HP
    7. 107971
    Prev
    Next
    INDEX
    Explanations

    Code or scientific data

    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
    hurst
    -0.28
    LIGHT
    -0.26
    追ãģĦ
    -0.25
    ðŁĺĦ
    -0.25
    .Rem
    -0.25
    %-
    -0.24
    åįĹçľģ
    -0.24
     Lighting
    -0.24
    Regression
    -0.24
    çħ§æĺİ
    -0.23
    POSITIVE LOGITS
    æ°¸
    0.28
    oret
    0.27
     Tablet
    0.26
    ies
    0.26
    inati
    0.24
     convention
    0.24
    acco
    0.24
    ned
    0.23
    .Platform
    0.23
     Han
    0.23
    Activations Density 57.458%

    No Known Activations