© 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. 4376
    Prev
    Next
    INDEX
    Explanations

    is a list of

    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
    转载èĩ³
    -0.09
    wares
    -0.08
    ếu
    -0.07
    yor
    -0.07
    kaw
    -0.07
    ç®ĹäºĨ
    -0.07
     putin
    -0.07
    irit
    -0.07
     cá»ĵn
    -0.07
    设计ä¸Ĭ
    -0.07
    POSITIVE LOGITS
    èĻĶ
    0.07
     exer
    0.06
     fru
    0.06
    æĪĸéĥ¨åĪĨ
    0.06
    渤
    0.06
    ear
    0.06
    å´ĩ
    0.06
    yped
    0.06
    æķ°æį®åŃĺåĤ¨
    0.06
    æ¡Ĩ
    0.06
    Activations Density 0.037%

    No Known Activations