© 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. 10407
    Prev
    Next
    INDEX
    Explanations

    numbers and years

    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
    ANJI
    -0.08
    è´¼
    -0.08
    ocities
    -0.07
     Enlight
    -0.07
    éķ¿çĶŁ
    -0.07
    bolt
    -0.07
    scha
    -0.07
    å¼ı设计
    -0.07
    è³Ĭ
    -0.06
    reece
    -0.06
    POSITIVE LOGITS
    æģ¯çļĦ
    0.09
    æģ¯
    0.08
    nable
    0.08
    çĻ½æ°´
    0.07
    adia
    0.07
    hode
    0.07
    gnu
    0.07
    able
    0.07
    æݧ
    0.07
    æİ¥è¿ij
    0.07
    Activations Density 0.084%

    No Known Activations