© 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. 13717
    Prev
    Next
    INDEX
    Explanations

    i leading to math notation or code imports

    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
    _CTL
    -0.07
    issor
    -0.07
    ä¹ĭå®Ŀ
    -0.06
    æ¯ĶæѦ
    -0.06
    /oauth
    -0.06
    æī¶è´«å¼Ģåıij
    -0.06
     liá»ĩu
    -0.06
    enti
    -0.06
    交ä¼ļ
    -0.06
    磮
    -0.06
    POSITIVE LOGITS
    zaak
    0.08
    çIJ´
    0.08
    asha
    0.08
    licherweise
    0.08
    _helpers
    0.07
    onel
    0.07
    ly
    0.07
    волÑĮ
    0.07
    umps
    0.07
    waves
    0.07
    Activations Density 0.001%

    No Known Activations