© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 60065
    Prev
    Next
    INDEX
    Explanations

    keyword following #

    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
    èĬľ
    -0.07
    çĴĥ
    -0.06
    èµ°
    -0.06
    --,
    -0.06
    éĤ®å¯Ħ
    -0.06
     замÑĭ
    -0.06
    _annotations
    -0.06
    æŃ£ç¾©
    -0.06
    aze
    -0.06
     ÙĨا
    -0.06
    POSITIVE LOGITS
     insomma
    0.08
    zan
    0.08
    opak
    0.08
    icamente
    0.08
    LESS
    0.07
    è¿İçĿĢ
    0.07
    è¿Ļæł·ä¸Ģç§į
    0.07
    çľĭè§ģäºĨ
    0.07
     Steph
    0.07
    è¿ĻäºĽä¿¡æģ¯
    0.07
    Activations Density 0.002%

    No Known Activations