© 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. 3904
    Prev
    Next
    INDEX
    Explanations

    -specific, -driven, -mediated, -induced

    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
    panse
    -0.08
    imizer
    -0.08
    stände
    -0.08
    comings
    -0.08
    oli
    -0.07
    ÛĮکا
    -0.07
    ãģ®ãģĭãĤĤãģĹãĤĮ
    -0.07
    -but
    -0.07
    semblies
    -0.07
    /latest
    -0.07
    POSITIVE LOGITS
    -dependent
    0.13
    -driven
    0.13
    -based
    0.13
    -related
    0.11
    -oriented
    0.11
    -mediated
    0.10
    _based
    0.10
    驱åĬ¨çļĦ
    0.10
    -focused
    0.10
    -
    0.09
    Activations Density 0.601%

    No Known Activations