© 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. 63479
    Prev
    Next
    INDEX
    Explanations

    tai chi

    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
    éĵģè¡Ģ
    -0.09
    èĨĽ
    -0.08
    ä¸Ģç«Ļ
    -0.08
    檬
    -0.08
    çĬ¯äºº
    -0.07
    åĭµ
    -0.07
     sins
    -0.07
    fid
    -0.07
     fid
    -0.07
     mú
    -0.07
    POSITIVE LOGITS
    éģĵ家
    0.14
    æĹłä¸º
    0.12
    èĢģåŃIJ
    0.10
    éĢįéģ¥
    0.09
    èĻļæĹł
    0.09
    éģĵæķĻ
    0.09
    顺åºĶ
    0.08
    åºĦåŃIJ
    0.08
    çİĦ
    0.08
    顺åħ¶èĩªçĦ¶
    0.08
    Activations Density 0.011%

    No Known Activations