© 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. 63282
    Prev
    Next
    INDEX
    Explanations

    numbers and scientific notation

    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
    utti
    -0.07
    sex
    -0.07
    汶
    -0.07
     accent
    -0.06
     landmark
    -0.06
    å¸ĥä»Ģ
    -0.06
     arrog
    -0.06
     paired
    -0.06
    æĿŁæīĭ
    -0.06
    ianto
    -0.06
    POSITIVE LOGITS
    Ń
    0.09
    ä¸ŃåĽ½å®¶
    0.08
    udir
    0.07
    minos
    0.07
    [email
    0.07
    类游æĪı
    0.07
    å®ļçķª
    0.07
    à¸Ľà¸°
    0.07
    XD
    0.07
    erdings
    0.07
    Activations Density 0.021%

    No Known Activations