© 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. 63792
    Prev
    Next
    INDEX
    Explanations

    Tail

    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
    åİķ
    -0.28
    onen
    -0.26
    ounder
    -0.26
    readonly
    -0.26
    leans
    -0.26
    iones
    -0.24
    wen
    -0.24
    åºĸ
    -0.23
    èī°
    -0.23
    ations
    -0.23
    POSITIVE LOGITS
    rzy
    0.27
     Lap
    0.26
    ='${
    0.24
    éºĿ
    0.24
    _bases
    0.23
     lap
    0.23
    adol
    0.23
    /umd
    0.23
    åŃĺåľ¨éĹ®é¢ĺ
    0.23
    è¿Ļæł·åģļ
    0.23
    Activations Density 16.409%

    No Known Activations