© 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. 41367
    Prev
    Next
    INDEX
    Explanations

    list separators and formatting

    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
    rog
    -0.06
    ÑĢева
    -0.06
    课åīį
    -0.06
    izzer
    -0.06
    æĿĢçļĦ
    -0.06
    ög
    -0.06
    orde
    -0.06
    ighton
    -0.06
     MOD
    -0.06
    æĶ¯æĮģ
    -0.06
    POSITIVE LOGITS
    bey
    0.09
    ellt
    0.08
    acea
    0.08
    èµ°åĪ°
    0.08
    è¿ŀäºij
    0.08
    elist
    0.08
    Located
    0.07
    å¿ĺ
    0.07
    Outlet
    0.07
    RelativeTo
    0.07
    Activations Density 0.001%

    No Known Activations