© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 39757
    Prev
    Next
    INDEX
    Explanations

    drawing, methods, text, code, names

    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
    à§įদ
    -0.07
    ooky
    -0.06
    uvi
    -0.06
     má»±c
    -0.06
    åħ·æľīçĭ¬ç«ĭ
    -0.06
    chwitz
    -0.06
    igator
    -0.06
    ÑĤÑĬ
    -0.06
    ariat
    -0.06
    adona
    -0.06
    POSITIVE LOGITS
    çŁ¥ä¹İ
    0.08
    warz
    0.07
    ankan
    0.07
    vore
    0.07
    à¸Ļม
    0.06
    enate
    0.06
    _estimator
    0.06
    mates
    0.06
    æĿĤ
    0.06
    елÑı
    0.06
    Activations Density 0.001%

    No Known Activations