© 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. 107015
    Prev
    Next
    INDEX
    Explanations

    coding questions/descriptions

    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
    arez
    -0.29
    æĪĺå½¹
    -0.26
    apore
    -0.25
    ẩu
    -0.25
    èĪ«
    -0.25
    éĻ¤å¤ĸ
    -0.25
    ocols
    -0.24
     Colt
    -0.24
    .po
    -0.24
    ypad
    -0.24
    POSITIVE LOGITS
    éĢĤ
    0.26
     reput
    0.25
    èĻ½
    0.24
    ialis
    0.24
     Äijây
    0.24
    ä¸įéĢĤ
    0.24
     Complex
    0.24
    elling
    0.23
    该
    0.23
    BufferSize
    0.23
    Activations Density 1.575%

    No Known Activations