© 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. 41925
    Prev
    Next
    INDEX
    Explanations

    quadrilateral, quadrant, quadratic, quadgrams, quadcopter

    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
    ä½Ĩä¸įéĻIJäºİ
    -0.08
    缸è¾ħ缸æĪIJ
    -0.07
    rica
    -0.07
    åľ¨çľī
    -0.07
    cept
    -0.07
     sire
    -0.07
    kena
    -0.07
    rike
    -0.07
    èĻ
    -0.06
    FIN
    -0.06
    POSITIVE LOGITS
    isci
    0.08
     kÃŃn
    0.08
    çī©è¯Ń
    0.08
    eric
    0.08
    æĪĸå¤ļ
    0.08
    غÙĦ
    0.07
     Ùģض
    0.07
    Ŀ
    0.07
    amour
    0.07
    inous
    0.07
    Activations Density 0.003%

    No Known Activations