© 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. 30382
    Prev
    Next
    INDEX
    Explanations

    common denominator

    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±ħå¤ļ
    -0.08
    èĭ±æĸĩåIJįåŃĹ
    -0.07
    еÑģÑĤво
    -0.07
    ÑĪне
    -0.07
    grama
    -0.07
    éģĹ
    -0.07
    åľ¨å¿ħ
    -0.06
    éĻIJãĤĬ
    -0.06
     repe
    -0.06
    讳
    -0.06
    POSITIVE LOGITS
    theses
    0.08
    èĴ¿
    0.07
    ãĤį
    0.07
    ä½ĵéªĮé¦Ĩ
    0.07
     denomin
    0.07
     denominator
    0.07
    æĹ¥è®°
    0.07
    alit
    0.07
    Factor
    0.07
    ugi
    0.07
    Activations Density 0.005%

    No Known Activations