© 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. 56431
    Prev
    Next
    INDEX
    Explanations

    programming constructs and keywords

    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
    éĩijæ¡¥
    -0.08
    chini
    -0.08
    mods
    -0.08
    馬æĭī
    -0.07
    (Pos
    -0.07
    _ENCODE
    -0.07
    eler
    -0.07
    æĶ¯æĮģä¸ĭ
    -0.07
    缴éĢļ车
    -0.07
    thouse
    -0.07
    POSITIVE LOGITS
    æŁ¥
    0.08
     Cong
    0.07
    访
    0.07
    unga
    0.07
    ä¿¡æģ¯æŁ¥è¯¢
    0.07
    çłĶ究åıijçİ°
    0.07
    访éĹ®
    0.07
     Briggs
    0.06
    uto
    0.06
    JA
    0.06
    Activations Density 0.115%

    No Known Activations