© 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. 845
    Prev
    Next
    INDEX
    Explanations

    negative outcomes or results

    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
    udd
    -0.07
    çĽĸä¸ĸ
    -0.07
    ãģ§ãģĻãģijãģ©
    -0.07
    åĽłä¸ºåıªæľī
    -0.07
     inutil
    -0.06
    pom
    -0.06
    ãģ§ãģĻãģĹ
    -0.06
    ç¿°
    -0.06
    elsen
    -0.06
     further
    -0.06
    POSITIVE LOGITS
     typically
    0.17
     commonly
    0.16
     usually
    0.15
    éĢļ常æĺ¯
    0.15
    typically
    0.14
    éĢļ常为
    0.14
    éĢļ常
    0.14
     Typically
    0.14
    Typ
    0.14
     often
    0.14
    Activations Density 0.249%

    No Known Activations