© 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. 30208
    Prev
    Next
    INDEX
    Explanations

    line or chart

    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
    ly
    -0.09
    ï¸İ
    -0.08
    ness
    -0.08
    ÏĤ
    -0.08
    teen
    -0.08
    ren
    -0.08
    леÑģ
    -0.08
    ellan
    -0.07
    缸è¾ħ缸æĪIJ
    -0.07
    nya
    -0.07
    POSITIVE LOGITS
    arity
    0.15
    ãĥĬãĥĥãĥĹ
    0.12
    ollipop
    0.10
    fty
    0.10
    段çļĦ
    0.09
    haul
    0.09
    ÑĩаÑĤ
    0.09
    hood
    0.09
    ìĸ´ëĵľ
    0.09
    ÙĪØ·
    0.09
    Activations Density 0.094%

    No Known Activations