© 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. 26342
    Prev
    Next
    INDEX
    Explanations

    effective or valid usage

    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
    er
    -0.12
    hower
    -0.10
    eranno
    -0.09
    oidal
    -0.09
    valho
    -0.09
    quel
    -0.08
    缸è¾ħ缸æĪIJ
    -0.08
    erÃŃa
    -0.08
    ยิà¸Ļà¸Ķี
    -0.08
    à¦ŀà§įà¦ľ
    -0.08
    POSITIVE LOGITS
    ity
    0.09
    kope
    0.08
    skr
    0.08
    nes
    0.08
    sworth
    0.07
    åľ°åİ»
    0.07
    æĶ¾çŁ¢
    0.07
    ÑĤ
    0.07
    رÙĪÙĨ
    0.07
    лÑİ
    0.07
    Activations Density 0.002%

    No Known Activations