© 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. 129582
    Prev
    Next
    INDEX
    Explanations

    is

    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
    åŃĺåľ¨çļĦ
    -0.29
    屯
    -0.28
    æ¬ºè´Ł
    -0.28
    ominated
    -0.27
    oy
    -0.27
    åľ¨ä»ĸ
    -0.26
    ASSERT
    -0.26
    ãģª
    -0.26
     rests
    -0.26
     Pur
    -0.25
    POSITIVE LOGITS
     motivo
    0.25
    าว
    0.25
     OSD
    0.25
    ivamente
    0.25
    matter
    0.25
    rok
    0.24
    ickness
    0.24
    ="?
    0.24
    /org
    0.24
    umps
    0.24
    Activations Density 16.184%

    No Known Activations