© 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. 64104
    Prev
    Next
    INDEX
    Explanations

    answering questions

    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
    istique
    -0.27
    alties
    -0.26
    åľ¨ä»ĸ
    -0.25
    ìĦŃ
    -0.25
    иÑĨÑĭ
    -0.25
    .cy
    -0.24
    xEE
    -0.24
    ADM
    -0.24
     Bring
    -0.23
    RTL
    -0.23
    POSITIVE LOGITS
    broken
    0.29
    交
    0.28
    å®Įæķ´çļĦ
    0.27
    fully
    0.26
    slot
    0.25
    "..
    0.24
    yon
    0.24
    å®ĮåĸĦçļĦ
    0.24
    ä»»æĦı
    0.24
    æ°Ĺ軽ãģ«
    0.24
    Activations Density 9.631%

    No Known Activations