© 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. 41670
    Prev
    Next
    INDEX
    Explanations

    abbreviations

    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
    erot
    -0.08
    apas
    -0.08
    æĮ¯
    -0.07
     occas
    -0.07
    kens
    -0.07
     NYT
    -0.07
     Dems
    -0.07
    æĬĬä»ĸçļĦ
    -0.07
    建è¡Į
    -0.07
    &C
    -0.07
    POSITIVE LOGITS
    ç®Ģ称
    0.10
    以ä¸ĭç®Ģ称
    0.09
     United
    0.08
     (“
    0.08
    United
    0.08
     (
    0.07
     abbreviated
    0.07
    abbrev
    0.07
     (__
    0.07
    abbr
    0.06
    Activations Density 1.891%

    No Known Activations