© 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. 19317
    Prev
    Next
    INDEX
    Explanations

    service marks and APIs

    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
    åĽŀäºĭ
    -0.08
    indsight
    -0.08
    entifier
    -0.07
    à¥ĭर
    -0.07
    ersistence
    -0.07
    å½¢çļĦ
    -0.07
    auptsächlich
    -0.07
    ogliono
    -0.07
    ìĶ©
    -0.07
    trer
    -0.07
    POSITIVE LOGITS
    .UserService
    0.09
    ign
    0.09
    (Service
    0.08
    æıIJä¾ĽèĢħ
    0.08
    ally
    0.08
     доÑģÑĤавки
    0.08
    enza
    0.08
    tlement
    0.07
    ÏĦεί
    0.07
    iro
    0.07
    Activations Density 0.100%

    No Known Activations