© 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. 29425
    Prev
    Next
    INDEX
    Explanations

    [number/bracket] reference

    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
    è¹
    -0.07
    arat
    -0.07
    åĽł
    -0.07
    zeb
    -0.07
    æİ¢
    -0.07
    éĻ¤
    -0.06
    _ordered
    -0.06
    çļĦåIJĮ
    -0.06
    etz
    -0.06
    çĬ¶åĨµ
    -0.06
    POSITIVE LOGITS
    è¯ł
    0.08
    ingly
    0.07
    âĢij
    0.07
    née
    0.07
    gett
    0.07
    åĻ¨çŃī
    0.07
    çĿĢèĦ¸
    0.07
    etta
    0.07
     cited
    0.07
    åħįè´¹åľ¨çº¿
    0.07
    Activations Density 0.002%

    No Known Activations