© 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. 25-TRANSCODER-HP
    7. 107769
    Prev
    Next
    INDEX
    Explanations

    spot

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_25.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.25.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    媳
    -0.28
    (comm
    -0.26
    gó
    -0.25
    logy
    -0.24
    waukee
    -0.24
     explos
    -0.24
    regor
    -0.23
    ãİı
    -0.23
    кова
    -0.23
    antic
    -0.23
    POSITIVE LOGITS
    idian
    0.26
    è´£
    0.24
    ä¾Ŀçħ§
    0.24
    ç«Ļ
    0.24
    ãĤ¿ãĥ³
    0.24
    аÑģÑĤ
    0.23
    太
    0.23
    cop
    0.23
    å¡«è¡¥
    0.23
    ç²¾åĩĨ
    0.23
    Activations Density 0.070%

    No Known Activations