© 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. 12237
    Prev
    Next
    INDEX
    Explanations

    powering devices off/on

    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
    occhi
    -0.07
    åĨįåĪ©çĶ¨
    -0.07
    ει
    -0.07
    ÙĤابÙĦ
    -0.07
    æĵĤ
    -0.07
    ode
    -0.06
    è´
    -0.06
    æĿ¥æĬĵ
    -0.06
    سÙĩ
    -0.06
     PROGMEM
    -0.06
    POSITIVE LOGITS
    è¯ķè¿IJè¡Į
    0.09
    èĪįå¾Ĺ
    0.08
    é¢Ħç¥Ŀ
    0.07
     Bereits
    0.07
    çĤ¹ä»Ģä¹Ī
    0.07
    å¼Ģæľº
    0.07
    abin
    0.07
    igny
    0.07
    èĩªæ£Ģ
    0.07
    åĪ©äºŀ
    0.07
    Activations Density 0.049%

    No Known Activations