© 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. 31444
    Prev
    Next
    INDEX
    Explanations

    we have

    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
    agama
    -0.07
    ãģ¿
    -0.07
    /{
    -0.07
    лиÑģÑĤа
    -0.06
    odal
    -0.06
    alet
    -0.06
    ;m
    -0.06
    ä½łçľŁ
    -0.06
    ç¾İåĽ¾
    -0.06
    åľ¨ä¹İ
    -0.06
    POSITIVE LOGITS
     bahwa
    0.09
    оÑģÑĤи
    0.08
    ï¼ļ
    0.07
    éĺµéĺµ
    0.07
    åıªè¦ģæĪij们
    0.07
    æµ¦æ±Ł
    0.07
    :
    0.07
    åĪĢåīij
    0.07
    :\
    0.07
    allery
    0.07
    Activations Density 0.008%

    No Known Activations