© 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. 40589
    Prev
    Next
    INDEX
    Explanations

    separator characters

    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
    procs
    -0.09
    ARIA
    -0.09
    iley
    -0.09
    ERI
    -0.09
    ç³ĸæ°´
    -0.08
    Æ°a
    -0.08
    oghi
    -0.08
    åľ¨äº§åĵģ
    -0.08
    หู
    -0.08
    rray
    -0.08
    POSITIVE LOGITS
    an
    0.07
    br
    0.07
    bacher
    0.07
    man
    0.07
    ings
    0.07
    asz
    0.06
    ance
    0.06
    up
    0.06
    quate
    0.06
    è·¯
    0.06
    Activations Density 0.015%

    No Known Activations