© 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. 42971
    Prev
    Next
    INDEX
    Explanations

    legal or official documents

    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
    æ±Ĺ
    -0.08
    ais
    -0.07
    iov
    -0.06
     Fach
    -0.06
    eping
    -0.06
    éĻ¶
    -0.06
     Provid
    -0.06
    åIJ¸æ°´
    -0.06
    ogen
    -0.05
    ãĤ²
    -0.05
    POSITIVE LOGITS
    OfWork
    0.09
    æĮĿ
    0.08
    ä½ľåģĩ
    0.08
    Č
    0.08
    abaya
    0.07
    ISTRA
    0.07
    onden
    0.07
    åıĭçĪ±
    0.07
    åıijæ¶Īæģ¯
    0.07
    éģ¨
    0.07
    Activations Density 0.038%

    No Known Activations