© 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. 18576
    Prev
    Next
    INDEX
    Explanations

    nice

    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
    áĢ¸
    -0.09
    ries
    -0.08
    halt
    -0.08
    å¥½äºĽ
    -0.08
    anything
    -0.07
    æīĭåı¯
    -0.07
    inds
    -0.07
    heck
    -0.07
    ä»Ģä¹Īåij¢
    -0.07
    UCH
    -0.07
    POSITIVE LOGITS
    енÑĮ
    0.10
    eties
    0.09
    ified
    0.09
    翼翼
    0.08
    ifications
    0.08
    ification
    0.08
    yman
    0.08
    erweise
    0.07
    ifiable
    0.07
    åĪ·åĪ·
    0.07
    Activations Density 0.034%

    No Known Activations