© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 50166
    Prev
    Next
    INDEX
    Explanations

    well, you

    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
    åĽłä¸ºå¥¹
    -0.08
    ÑĥÑĢе
    -0.07
    åĽłä¸ºä»ĸ
    -0.07
     obiec
    -0.07
    utato
    -0.07
    utados
    -0.07
    ä½Ĩä¹Łæľī
    -0.07
     lans
    -0.07
    hora
    -0.07
    -hit
    -0.07
    POSITIVE LOGITS
     sö
    0.07
    æĬ±æŃī
    0.07
    ras
    0.07
    åIJĦé¡¹å·¥ä½ľçļĦ
    0.06
    bose
    0.06
    ..
    0.06
    æĢ»ä¹ĭ
    0.06
    å°±æĪIJ为
    0.06
    ium
    0.06
    çİĩè¾¾åĪ°
    0.06
    Activations Density 0.037%

    No Known Activations