© 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. 24-TRANSCODER-HP
    7. 149607
    Prev
    Next
    INDEX
    Explanations

    ho

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_24.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.24.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ropy
    -0.25
     Oro
    -0.24
    ä¾Ľ
    -0.24
    agoon
    -0.24
    è°´è´£
    -0.23
    оÑĩно
    -0.23
    iblings
    -0.23
     PUB
    -0.23
    icol
    -0.23
    Doctrine
    -0.23
    POSITIVE LOGITS
    对ä¸ŃåĽ½
    0.25
    wers
    0.25
    os
    0.24
    è¶ķ
    0.24
    带
    0.24
    we
    0.24
    wen
    0.24
    æ¦Ķ
    0.24
    äºĨä¸Ģ个
    0.23
     *[
    0.23
    Activations Density 1.385%

    No Known Activations