© 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. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 51251
    Prev
    Next
    INDEX
    Explanations

    names in quotes or paths

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tig
    -0.07
    .trans
    -0.07
    å°Ķå¾·
    -0.06
    æµ·çĩķ
    -0.06
    鼨çļĦ
    -0.06
    éĩijæ¦ľ
    -0.06
    鼨ä¸Ń
    -0.06
    umon
    -0.06
    ä¸Ģå¿ĥ
    -0.06
    ìĸ´ëĤĺ
    -0.06
    POSITIVE LOGITS
    æ²®
    0.09
    pai
    0.08
    幻影
    0.07
    enor
    0.07
    ayet
    0.07
    auen
    0.07
    ä»Ķ
    0.06
    linky
    0.06
    lash
    0.06
    æĿł
    0.06
    Activations Density 0.123%

    No Known Activations