© 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. 17073
    Prev
    Next
    INDEX
    Explanations

    whose properties

    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
    llen
    -0.08
    å¾·åĪ©
    -0.07
    ä¸ŃåĽ½åĽ½éĻħ
    -0.07
    ë¥ĺ
    -0.07
    tribu
    -0.07
    é«ĺä½İ
    -0.07
     respe
    -0.07
    åĩĨ
    -0.07
    oling
    -0.07
    å©´
    -0.07
    POSITIVE LOGITS
     whose
    0.12
     اÙĦتÙĬ
    0.10
     yang
    0.10
     cuyos
    0.09
     ÏĢοÏħ
    0.09
    whose
    0.09
     that
    0.09
    áŀĬáŁĤáŀĽ
    0.09
     اÙĦتÙī
    0.09
     who
    0.09
    Activations Density 0.368%

    No Known Activations