© 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. 16830
    Prev
    Next
    INDEX
    Explanations

    directions, regions, states

    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
    mati
    -0.08
    tones
    -0.08
    æĥħåĨµåĪĨæŀIJ
    -0.08
    å±ķçİ°åľ¨
    -0.08
    hem
    -0.08
    å¹´å§ĭ
    -0.07
    eor
    -0.07
     siquiera
    -0.07
    )).
    -0.07
    дÑĢи
    -0.07
    POSITIVE LOGITS
     _______,
    0.07
     sekaligus
    0.06
    ãģ§ãģĤãĤĬ
    0.06
    ãģłãģijãģ§ãģªãģı
    0.06
    èĢĮ没æľī
    0.06
    ä¸įèĻļ
    0.06
     ê²ĥìĿ´ê³ł
    0.06
     certes
    0.06
    èĢĮéĿŀ
    0.06
    èĢĮä¸Ķè¦ģ
    0.06
    Activations Density 0.045%

    No Known Activations