© 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. 14496
    Prev
    Next
    INDEX
    Explanations

    unit or aggregate component

    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
    è°
    -0.08
    ster
    -0.07
    å¥ī
    -0.07
    aid
    -0.07
    ossal
    -0.07
    æķ¢
    -0.07
    awat
    -0.06
    缸éĢ¢
    -0.06
     encontr
    -0.06
     Giles
    -0.06
    POSITIVE LOGITS
    æīĵåĮħ
    0.10
    åĽ¢
    0.09
    ä½ľä¸ºä¸Ģ个
    0.09
    agg
    0.08
    å°ģè£ħ
    0.08
    è§Ĩä½ľ
    0.08
    å¡Į
    0.08
    aggregate
    0.08
    åĽ¢çļĦ
    0.08
    eln
    0.08
    Activations Density 0.027%

    No Known Activations