© 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. 56047
    Prev
    Next
    INDEX
    Explanations

    Gy amounts or rates

    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
    rem
    -0.07
    rec
    -0.06
    bia
    -0.06
    pler
    -0.06
     Tam
    -0.06
    OU
    -0.06
    ç¼ļ
    -0.06
    æľīä¸Ń
    -0.06
    ench
    -0.06
    hl
    -0.06
    POSITIVE LOGITS
    hips
    0.08
    atings
    0.08
    arz
    0.08
    ä¸įæĦģ
    0.08
    ARGS
    0.08
    æħĭ
    0.08
    achsen
    0.08
    ingue
    0.08
    à¹Ħล
    0.08
    媳
    0.07
    Activations Density 0.006%

    No Known Activations