© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 37615
    Prev
    Next
    INDEX
    Explanations

    point of view

    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
    Negative Logits
     جÙĦ
    -0.08
    egah
    -0.08
    Ģ
    -0.08
    »
    -0.08
    trinsic
    -0.07
    egie
    -0.07
    عÙħ
    -0.07
    umpt
    -0.07
    idebar
    -0.07
    _Mode
    -0.07
    POSITIVE LOGITS
    å®Įæķ´çļĦ
    0.07
    åħ¨éĿ¢çļĦ
    0.07
    à¸Ńà¸Ķ
    0.06
    èŀįåIJĪäºĨ
    0.06
    åħĪè¡Į
    0.06
    æľīåĩłä¸ª
    0.06
    ily
    0.06
    MARK
    0.06
    å®Įæķ´
    0.06
    éĽªçĻ½çļĦ
    0.06
    Activations Density 0.001%

    No Known Activations