© 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. 33286
    Prev
    Next
    INDEX
    Explanations

    mathematical variables

    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
    éĢı
    -0.08
    attes
    -0.08
    åĢ¾
    -0.08
    è·¯éĢı
    -0.07
    æ¸
    -0.07
    structuring
    -0.07
    éģ®
    -0.07
    è§ij
    -0.07
    æīijéĿ¢
    -0.07
    ä¸įå¿į
    -0.07
    POSITIVE LOGITS
    uvi
    0.07
    çĤİçĤİ
    0.06
     Pah
    0.06
    ê¸ī
    0.06
    ntag
    0.06
    rine
    0.06
    é£İèĥ½
    0.06
    ä¸½å¨ľ
    0.06
     oso
    0.06
    è¿ĶåĽŀåĪĹ表
    0.06
    Activations Density 0.028%

    No Known Activations