© 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. 45840
    Prev
    Next
    INDEX
    Explanations

    Holder's Theorem, Plancherel's theorem, Cauchy integral

    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
    ëĿ¼ìļ´
    -0.08
    å·¡è§Ĩåijĺ
    -0.07
    osit
    -0.07
    .rmi
    -0.07
    ina
    -0.07
    akil
    -0.07
    æĢ§åľ°
    -0.06
    iated
    -0.06
    iates
    -0.06
     elsif
    -0.06
    POSITIVE LOGITS
    irk
    0.08
    ombat
    0.08
    midt
    0.07
    inte
    0.07
    ramer
    0.07
    bacher
    0.07
    詹
    0.07
    neider
    0.07
     pairs
    0.07
    ç¡®ä¿ĿäºĨ
    0.07
    Activations Density 0.003%

    No Known Activations