© 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. 27291
    Prev
    Next
    INDEX
    Explanations

    locations

    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
    -0.07
    atl
    -0.07
    éĩijçŁ³
    -0.07
    omb
    -0.06
    (for
    -0.06
    æľīå¤ļ大
    -0.06
    好åij¢
    -0.06
     ведениÑı
    -0.06
    NumberOf
    -0.06
    itor
    -0.06
    POSITIVE LOGITS
    ascript
    0.07
    à´ĸ
    0.07
     lic
    0.07
    -scripts
    0.07
     anale
    0.07
    POSIT
    0.07
    å¤Ħäºİ
    0.07
    xde
    0.07
    reib
    0.07
     Ell
    0.07
    Activations Density 0.001%

    No Known Activations