© 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. 39110
    Prev
    Next
    INDEX
    Explanations

    F following numbers

    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
     Fanpage
    -0.08
    getApplication
    -0.08
    鼰
    -0.08
    å½¢åĬ¿
    -0.07
    uzu
    -0.07
    اک
    -0.07
    è½¬è½½çĽ®çļĦåľ¨äºİä¼łéĢĴæĽ´å¤ļä¿¡æģ¯
    -0.07
    éĽ°åĽ²
    -0.07
    buff
    -0.07
    esub
    -0.07
    POSITIVE LOGITS
    nets
    0.06
     inline
    0.06
    æĹ
    0.06
    yj
    0.06
     cum
    0.06
    éĽ
    0.06
    ã
    0.06
     Jonas
    0.06
    åIJİéĿ¢
    0.06
     Pacific
    0.05
    Activations Density 0.062%

    No Known Activations