© 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. 60183
    Prev
    Next
    INDEX
    Explanations

    math expressions with numbers

    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
    代ä¹ĭ
    -0.07
    æīĭæĦŁ
    -0.07
    adow
    -0.07
    prot
    -0.07
    éĶĻ误æĪĸ
    -0.07
    é¤IJ
    -0.06
    _PROTOCOL
    -0.06
    ±
    -0.06
    ä¸ĭä¸Ģ页
    -0.06
    only
    -0.06
    POSITIVE LOGITS
    GRA
    0.08
    èĪĨ
    0.07
    æłĩçļĦ
    0.07
    Ïħμα
    0.07
    azar
    0.07
    积æŀģå¼Ģå±ķ
    0.07
    ÐĿС
    0.07
    teca
    0.07
    icine
    0.07
    иÑĤаÑĢ
    0.07
    Activations Density 0.008%

    No Known Activations