© 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. 26329
    Prev
    Next
    INDEX
    Explanations

    `[@B` citations

    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
    üz
    -0.07
    ajor
    -0.07
    isas
    -0.06
    åĽ¢åĽ¢
    -0.06
    agem
    -0.06
    æĶ¶åĽŀ
    -0.06
    æīĢå±ŀ
    -0.06
    çĪ¸çĪ¸è¯´
    -0.06
    ิส
    -0.06
    apter
    -0.06
    POSITIVE LOGITS
    并ä¸į容æĺĵ
    0.08
    并ä¸įä¼ļ
    0.08
    पà¥įत
    0.08
    ACHED
    0.07
    çªĿ
    0.07
    OUCH
    0.07
    orb
    0.07
     hale
    0.07
    archs
    0.07
    并ä¸į
    0.07
    Activations Density 0.017%

    No Known Activations