© 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. 29994
    Prev
    Next
    INDEX
    Explanations

    numeric formatting and calculation

    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
    _deep
    -0.07
    åķ¸
    -0.07
    aily
    -0.07
    éºŁ
    -0.07
    azel
    -0.06
    phin
    -0.06
    /grpc
    -0.06
     alph
    -0.06
    jat
    -0.06
    Õ¡Öģ
    -0.06
    POSITIVE LOGITS
    çŁ³æ¦´
    0.08
    éĤ£åº§
    0.07
    鲨
    0.07
    ELTS
    0.07
    éĤ£çīĩ
    0.07
    ä¸įä¼ij
    0.07
    combe
    0.07
    å±ħæĺĵ
    0.07
    olarity
    0.07
    éĤĢ
    0.07
    Activations Density 0.004%

    No Known Activations