© 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. Qwen3.5-4B
    5. 15-RES-MATRYOSHKA-65K
    7. 17359
    Prev
    Next
    INDEX
    Explanations

    stimulating nerve signals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    decoderesearch/qwen-3.5-saes/qwen-3.5-4b
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ed
    -0.10
    ing
    -0.08
    ingk
    -0.08
    Rép
    -0.07
    è²Į
    -0.07
    stead
    -0.07
    itud
    -0.07
    edly
    -0.07
    inals
    -0.07
    WER
    -0.07
    POSITIVE LOGITS
    ult
    0.06
     viv
    0.05
    ulated
    0.05
    γά
    0.05
    hoa
    0.05
    insky
    0.05
    åĻ¨çļĦ
    0.05
     lưỡng
    0.05
    ä¸Ĭæ¼Ķ
    0.05
    TL
    0.05
    Activations Density 0.027%

    No Known Activations