© 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. 61548
    Prev
    Next
    INDEX
    Explanations

    claims priority

    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
    anny
    -0.08
     Below
    -0.06
    çīµ
    -0.06
    خب
    -0.06
    ä¸ĭä¸Ģ次
    -0.06
     Sharp
    -0.06
    atcher
    -0.06
    æİ§ç³»ç»Ł
    -0.06
    çīµçĿĢ
    -0.06
    akes
    -0.06
    POSITIVE LOGITS
    rer
    0.08
    olet
    0.08
    æĺĮåİ¿
    0.08
    使æĪij
    0.07
     grate
    0.07
     manus
    0.07
    ´Ī
    0.07
     volna
    0.07
    å¢ŀè¿ĽäºĨ
    0.07
     manuscript
    0.07
    Activations Density 0.180%

    No Known Activations