© 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. 30752
    Prev
    Next
    INDEX
    Explanations

    conduct conducting conductive conductors

    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
    ами
    -0.09
    hood
    -0.08
    ê¾¼
    -0.07
    fication
    -0.07
    纷åijĪ
    -0.07
    -même
    -0.07
    ugin
    -0.07
    дне
    -0.07
    à¸İ
    -0.07
    -0.06
    POSITIVE LOGITS
    ãĤ¥
    0.11
    ivities
    0.10
    ress
    0.09
    erait
    0.09
    PILE
    0.09
    ives
    0.09
    имоÑģÑĤÑĮ
    0.09
    ãĥ³
    0.09
    ively
    0.09
    еÑĢж
    0.08
    Activations Density 0.045%

    No Known Activations