© 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. 64740
    Prev
    Next
    INDEX
    Explanations

    real world applications

    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
    ukul
    -0.07
     åt
    -0.07
    arias
    -0.07
     overall
    -0.07
    æķ´ä½ĵä¸Ĭ
    -0.07
    berra
    -0.07
    ahui
    -0.07
    _PRESENT
    -0.07
    ÙĪÙħÙĬØ©
    -0.07
    raphe
    -0.07
    POSITIVE LOGITS
    (real
    0.10
    å®ŀéĻħæĥħåĨµ
    0.09
     practice
    0.09
    羣å®ŀçļĦ
    0.09
    å®ŀéĻħ
    0.09
    æĥħå¢ĥ
    0.09
     implementation
    0.08
     situations
    0.08
     scenarios
    0.08
    å®ŀè·µä¸Ń
    0.08
    Activations Density 0.050%

    No Known Activations