© 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. 58286
    Prev
    Next
    INDEX
    Explanations

    version indicator or deprecation notice

    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
    ç»ı常æĢ§
    -0.07
    angan
    -0.07
    åįĬæľĪ
    -0.07
    主è¦ģç»ıèIJ¥
    -0.07
    hren
    -0.07
     Ñģан
    -0.07
     Ud
    -0.07
    é«ĺè¿ľ
    -0.07
    UTI
    -0.07
    é£ŀæĿ¥
    -0.06
    POSITIVE LOGITS
     newer
    0.18
     outdated
    0.17
     obsolete
    0.17
    æŧ
    0.17
     older
    0.17
     modern
    0.16
     old
    0.16
     legacy
    0.15
    -era
    0.15
    èĪĬ
    0.15
    Activations Density 1.229%

    No Known Activations