© 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. 25593
    Prev
    Next
    INDEX
    Explanations

    excited state

    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
    istik
    -0.09
    ä¸Ĭä¸ĭçıŃ
    -0.08
    iog
    -0.08
    olini
    -0.07
    èĬĿ
    -0.07
     grounding
    -0.07
    西æĸ¯
    -0.07
    foro
    -0.07
    ä¸įçĪ½
    -0.07
    æİ¥åľ°
    -0.07
    POSITIVE LOGITS
    setState
    0.07
    è¶Ĭé«ĺ
    0.07
    ucia
    0.07
    -exc
    0.07
     states
    0.07
     STATES
    0.07
    uchten
    0.07
     sustain
    0.07
    loat
    0.07
    æ¿Ģåıij
    0.06
    Activations Density 0.008%

    No Known Activations