© 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. 11106
    Prev
    Next
    INDEX
    Explanations

    that was said

    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
    å¸ĥæĸ¯
    -0.07
    sgi
    -0.07
    ')</
    -0.07
    _EM
    -0.07
    unner
    -0.07
    uvi
    -0.07
    tsy
    -0.07
    åĪ
    -0.06
    å¤ļ为
    -0.06
    vist
    -0.06
    POSITIVE LOGITS
    è¿Ŀåıįä¸Ĭè¿°
    0.08
     tehát
    0.08
     dunque
    0.07
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    0.07
    ä¹ŁåĽłæѤ
    0.07
    èĻ½çĦ¶åľ¨
    0.07
    è¿Ļæł·ä¸ĢæĿ¥
    0.07
    usz
    0.06
    |null
    0.06
    è£ħä¸Ĭ
    0.06
    Activations Density 0.017%

    No Known Activations