© 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. 11273
    Prev
    Next
    INDEX
    Explanations

    achieved by

    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
    æĸ°å±Ģ
    -0.08
    æŀ¶
    -0.07
    imest
    -0.07
     raise
    -0.07
    ilus
    -0.07
     جÙħ
    -0.07
    æ¯ħ
    -0.07
    itsu
    -0.07
    chn
    -0.06
    ä¸ĭéĿ¢å°±
    -0.06
    POSITIVE LOGITS
    iskan
    0.08
    tar
    0.07
    /latest
    0.07
    .closest
    0.07
    enom
    0.07
    ÑĢаÑģ
    0.07
    stown
    0.07
     enjo
    0.07
    ÑĦеÑĢа
    0.06
    uw
    0.06
    Activations Density 0.003%

    No Known Activations