© 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. 17762
    Prev
    Next
    INDEX
    Explanations

    `.commons` or `image`

    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
    chini
    -0.07
    stead
    -0.07
    خط
    -0.06
    biet
    -0.06
    iedad
    -0.06
    éĻ
    -0.06
    PACE
    -0.06
    çijŀå®ī
    -0.06
    ä¸Ģ身
    -0.06
    ÙĴÙĨÙİا
    -0.06
    POSITIVE LOGITS
    éĻĨç»Ń
    0.07
    stö
    0.07
    builtin
    0.07
    odb
    0.07
    çIJħ
    0.07
    odle
    0.07
    濯
    0.07
    åı¦å¤ĸä¸Ģ个
    0.07
    _NT
    0.06
    ãĤ¸ãĥ£ãĥ¼
    0.06
    Activations Density 0.009%

    No Known Activations