© 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. 17716
    Prev
    Next
    INDEX
    Explanations

    job vacancy

    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
    æĸ°ä¸ĸ纪
    -0.07
     Downing
    -0.06
    å¾ĪåıĹ
    -0.06
    æĥħæĦı
    -0.06
    ç»ıæµİ建设
    -0.06
     ei
    -0.06
    eldon
    -0.06
    ç´¢æĢ§
    -0.06
    _modified
    -0.06
    ä¼´ä½ł
    -0.06
    POSITIVE LOGITS
     urgently
    0.10
     freelancer
    0.10
     Freel
    0.09
    çİ°æľī
    0.09
     urgent
    0.09
    åĮħæĭ¬ä½Ĩä¸įéĻIJäºİ
    0.08
    åħ·ä½ĵè¦ģæ±Ĥ
    0.08
     freel
    0.08
    å·²ç»ıç»ĵæĿŁ
    0.08
     preferably
    0.08
    Activations Density 0.269%

    No Known Activations