© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 49960
    Prev
    Next
    INDEX
    Explanations

    Red Barn

    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
    å¾Ī好çľĭ
    -0.07
    èĢĮçŁ¥
    -0.07
    undu
    -0.07
    à¸Ļู
    -0.07
    ç¯Ģ
    -0.07
    kul
    -0.07
    utc
    -0.07
     Nol
    -0.07
    actly
    -0.07
    åħ¶èĩªçĦ¶
    -0.07
    POSITIVE LOGITS
    ilan
    0.06
    aglia
    0.06
    _PROF
    0.06
    urd
    0.06
    asiat
    0.06
     repeated
    0.06
    á»Ŀ
    0.06
    æĪijè¦ģè¯Ħ论
    0.06
    åŃ¦ä¹łä¸İ
    0.06
    èµ°éģį
    0.06
    Activations Density 0.002%

    No Known Activations