© 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. 65210
    Prev
    Next
    INDEX
    Explanations

    lisk account

    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
    <|box_end|>
    -0.10
    è¾¾æĸ¯
    -0.08
    unce
    -0.08
    çĭ¬ç§Ģ
    -0.07
    etime
    -0.07
    kini
    -0.07
    antik
    -0.07
    ulty
    -0.07
    é£İè¡Į
    -0.07
    嫦
    -0.07
    POSITIVE LOGITS
    s
    0.07
    اک
    0.07
    Ùħ
    0.07
    izont
    0.07
    volv
    0.06
     ÙĦÙĨ
    0.06
     */)
    0.06
    रà¥į
    0.06
    OPY
    0.06
    Ùĩ
    0.06
    Activations Density 0.056%

    No Known Activations