© 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. 23-TRANSCODER-HP
    7. 24871
    Prev
    Next
    INDEX
    Explanations

    dog

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_23.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.23.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    >{"
    -0.24
    æľīåĬ©
    -0.24
    sheets
    -0.23
    “.
    -0.23
    æĤ¨åIJĮæĦı
    -0.23
    urs
    -0.23
    vg
    -0.23
    æ¯Ķçİĩ
    -0.23
    æ¼±
    -0.23
    erv
    -0.23
    POSITIVE LOGITS
     step
    0.24
    late
    0.23
    继
    0.23
     Licensed
    0.22
     اÙĦتاÙĦÙĬ
    0.22
     term
    0.22
    lat
    0.22
    为æŃ¢
    0.22
    pile
    0.22
    为ä¹ĭ
    0.22
    Activations Density 0.158%

    No Known Activations