© 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. 12496
    Prev
    Next
    INDEX
    Explanations

    material types

    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
    _WP
    -0.09
    _POL
    -0.08
    人ä¸Ģ
    -0.07
    æ¦
    -0.07
    ingly
    -0.07
    _exists
    -0.07
    -caret
    -0.07
    estan
    -0.07
    ελ
    -0.07
    ücks
    -0.06
    POSITIVE LOGITS
    jala
    0.08
    imis
    0.08
     Chang
    0.07
    è½¬çľ¼
    0.07
    ordes
    0.07
    unta
    0.07
    ä¹Ŀéĩį
    0.07
    andom
    0.06
    FullScreen
    0.06
    ä¸Ńåįİ人æ°ijåħ±åĴĮåĽ½æ°ijäºĭè¯ī讼æ³ķ
    0.06
    Activations Density 0.613%

    No Known Activations