© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 23273
    Prev
    Next
    INDEX
    Explanations

    margin within CSS

    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
    деÑģÑıÑĤ
    -0.08
    orthy
    -0.08
    ück
    -0.08
     ì·¨
    -0.08
    asics
    -0.08
    uele
    -0.08
    zzle
    -0.07
    hood
    -0.07
    ë§ĪìŀIJ
    -0.07
    usic
    -0.07
    POSITIVE LOGITS
    kola
    0.07
     between
    0.07
    åīį款
    0.06
     BETWEEN
    0.06
    ä¸Ĭä¸ĭ
    0.06
    两æĹģ
    0.06
    imiz
    0.06
    æł¹æ·±
    0.06
    rr
    0.06
    omi
    0.06
    Activations Density 0.026%

    No Known Activations