© 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. 21363
    Prev
    Next
    INDEX
    Explanations

    examples using `.` or `(`

    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
    Ĥ¬
    -0.07
    eyer
    -0.07
    ç´ļ
    -0.07
    Å¡ov
    -0.07
    ware
    -0.07
    WARE
    -0.07
    åıijå±ķæĸ°
    -0.07
    丽ä¸Ŀ
    -0.07
    å°Ĩè¿Ļ
    -0.07
    ัย
    -0.07
    POSITIVE LOGITS
    åĭ¤äºİ
    0.07
     wel
    0.07
    .cf
    0.06
    çļĦåĢ¼
    0.06
     Moo
    0.06
    bezog
    0.06
    itek
    0.06
     pedido
    0.06
    volv
    0.06
     tarn
    0.06
    Activations Density 0.025%

    No Known Activations