© 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. 38906
    Prev
    Next
    INDEX
    Explanations

    proper nouns, often names

    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
     himself
    -0.07
    å°ıåŃIJ
    -0.07
     carrying
    -0.06
    åħĦå¼Łä»¬
    -0.06
    éĿ¢
    -0.06
    idon
    -0.06
    leisten
    -0.06
    åįļ士åѦä½į
    -0.06
    æ¼Ķä¹ī
    -0.06
    çĻ¾ç§ijåħ¨ä¹¦
    -0.06
    POSITIVE LOGITS
    née
    0.10
     née
    0.09
     herself
    0.09
    åħ«æĸ¹
    0.08
    аниÑĨ
    0.08
     spokeswoman
    0.08
    astique
    0.08
    -caret
    0.08
    arani
    0.08
    rée
    0.08
    Activations Density 0.331%

    No Known Activations