© 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. 141958
    Prev
    Next
    INDEX
    Explanations

    Code snippets/documentation

    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
    åħĭæľį
    -0.30
    æł¹æį®ä¸įåIJĮ
    -0.29
    '],['
    -0.26
     ni
    -0.25
    olini
    -0.25
    æ¯ıéļĶ
    -0.25
    ');"
    -0.24
    Ni
    -0.24
    æĹĹ
    -0.24
     Ni
    -0.24
    POSITIVE LOGITS
     spoken
    0.26
    为ä¸Ńå¿ĥ
    0.26
    yne
    0.25
    stras
    0.24
     punched
    0.24
     inverted
    0.24
     unresolved
    0.24
     labeled
    0.24
     cháy
    0.23
     assisted
    0.23
    Activations Density 53.825%

    No Known Activations