© 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. 11700
    Prev
    Next
    INDEX
    Explanations

    code keywords and structures

    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
    ya
    -0.06
    stit
    -0.06
    asuk
    -0.06
    izi
    -0.06
    å¾Īåĸľæ¬¢
    -0.05
     Vorm
    -0.05
    è®®
    -0.05
    acken
    -0.05
    éĤ£ä¹Ī容æĺĵ
    -0.05
    neur
    -0.05
    POSITIVE LOGITS
    &W
    0.08
    ByExample
    0.08
    contents
    0.08
    avigator
    0.08
     инÑĭÑħ
    0.07
    æľīåħ³äºĭ项
    0.07
    AWN
    0.07
    पà¥ĭ
    0.07
    èĵ
    0.07
    èĭ¦è¾£
    0.07
    Activations Density 0.026%

    No Known Activations