© 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. 8126
    Prev
    Next
    INDEX
    Explanations

    programming code and configuration

    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
    kening
    -0.08
    ogenic
    -0.07
    yy
    -0.07
    ÑĢÑıн
    -0.07
    èĢĺ
    -0.07
    ogens
    -0.07
    ÑģÑĤин
    -0.07
    ipay
    -0.06
    ients
    -0.06
    china
    -0.06
    POSITIVE LOGITS
    βά
    0.06
    ende
    0.06
    hm
    0.06
     Falk
    0.06
    hme
    0.06
    åı¯ä»¥åIJĹ
    0.06
    éĿŀ常æĺİæĺ¾
    0.06
    utta
    0.06
    illot
    0.06
    å½±åĵįçĿĢ
    0.06
    Activations Density 0.221%

    No Known Activations