© 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. 65403
    Prev
    Next
    INDEX
    Explanations

    Kant, Schopenhauer, Law, SAP, Bach

    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
    ä»ĭ
    -0.08
    Insensitive
    -0.07
    воло
    -0.07
    inston
    -0.07
    æµ®
    -0.07
    _choices
    -0.07
    /swagger
    -0.07
    кÑĢе
    -0.07
    ັàºĻ
    -0.07
    contest
    -0.07
    POSITIVE LOGITS
    康德
    0.08
     Kant
    0.08
     Gag
    0.08
     instrument
    0.07
    èݱ
    0.07
    urb
    0.07
    GM
    0.07
    å¸Ń
    0.07
    æ³¢ç½Ĺ
    0.06
     Instrument
    0.06
    Activations Density 0.004%

    No Known Activations