© 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. 30994
    Prev
    Next
    INDEX
    Explanations

    ! Licensed

    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
    ä½Ĩä¸įéĻIJäºİ
    -0.15
    icolo
    -0.10
    à¦ĩ
    -0.10
    züg
    -0.10
    esh
    -0.09
    elor
    -0.09
    ãģ£ãģįãĤĬ
    -0.09
    ’T
    -0.09
    ↵      ↵
    -0.09
    etti
    -0.09
    POSITIVE LOGITS
    erk
    0.09
    ê¹IJ
    0.08
    om
    0.07
    деÑģÑı
    0.07
    s
    0.07
    erce
    0.07
    ern
    0.07
    to
    0.07
    -grey
    0.07
    erm
    0.07
    Activations Density 0.089%

    No Known Activations