© 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. 16127
    Prev
    Next
    INDEX
    Explanations

    SQL syntax and data types

    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
    åı¯æĤ²
    -0.07
    åı«å¥½
    -0.06
    çļĦè¿ĺæľī
    -0.06
    大æĥĬ
    -0.06
    mite
    -0.06
     alternate
    -0.06
    åĽłä¸ºåħ¶
    -0.06
    åı¯æĥ³
    -0.06
    åIJİå¤ĩ
    -0.06
    åį´ä¸įçŁ¥éģĵ
    -0.06
    POSITIVE LOGITS
    ekat
    0.09
    etta
    0.08
    ä¸Ģç«ł
    0.08
    evin
    0.07
    asher
    0.07
    è¿İ
    0.07
    åĴĮéĻĪ
    0.07
    alin
    0.07
    ä¸įæĸŃåĬłå¼º
    0.07
    à¹īาà¸ĩ
    0.07
    Activations Density 0.206%

    No Known Activations