© 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. 64272
    Prev
    Next
    INDEX
    Explanations

    Code/Data/File paths

    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
    otide
    -0.25
    olve
    -0.24
     groin
    -0.24
    <Renderer
    -0.23
    QObject
    -0.23
    æ²ĥ
    -0.23
    igion
    -0.23
    ç
    -0.23
    uencia
    -0.23
     Eag
    -0.23
    POSITIVE LOGITS
    LEV
    0.27
    /legal
    0.27
    å¿ħè¦ģçļĦ
    0.26
    è¯ĥ
    0.25
    æľīå¿ħè¦ģ
    0.25
    ä¿Ŀé²ľ
    0.25
     relevant
    0.25
    ten
    0.25
     Checklist
    0.25
    Seven
    0.24
    Activations Density 9.372%

    No Known Activations