© 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. 27145
    Prev
    Next
    INDEX
    Explanations

    saw how

    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
    ifar
    -0.09
    åħ¨åĨĽ
    -0.08
     ÐĴпÑĢоÑĩем
    -0.08
    Ø·ÙĬÙĨ
    -0.08
    èĢ¸
    -0.07
    åĪĨå¤ĸ
    -0.07
    éĽĨåĽ¢æĹĹä¸ĭ
    -0.07
     внезапно
    -0.07
    éĽĨåĽ¢èij£äºĭéķ¿
    -0.07
    ogr
    -0.07
    POSITIVE LOGITS
     evid
    0.07
    å
    0.07
    çļĻ
    0.07
    çļĦä¸ĢäºĽ
    0.07
     thru
    0.06
    ðŁĺĢ
    0.06
    ocene
    0.06
    Outlined
    0.06
    ureka
    0.06
    ault
    0.06
    Activations Density 0.391%

    No Known Activations