© 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. 43917
    Prev
    Next
    INDEX
    Explanations

    dates that follow punctuation

    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
    ingle
    -0.07
    \
    -0.07
     bul
    -0.06
    è¯ī
    -0.06
    LI
    -0.06
    son
    -0.06
     neither
    -0.06
    cese
    -0.06
    D
    -0.06
    erg
    -0.06
    POSITIVE LOGITS
    -navbar
    0.09
    ,DB
    0.08
    ITH
    0.08
    à¹Ģมืà¹Īà¸Ńวัà¸Ļà¸Ĺีà¹Ī
    0.08
    embro
    0.08
    kania
    0.07
    pkt
    0.07
    èı²å°Ķå¾·
    0.07
    ɵ
    0.07
    æľĢè¿ijæĽ´æĸ°
    0.07
    Activations Density 0.059%

    No Known Activations