© 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. 3139
    Prev
    Next
    INDEX
    Explanations

    evacuation, zinc, geometric, staffing, relations

    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
    为ä¸Ń
    -0.07
    åĿ¯
    -0.07
    èĥļ
    -0.07
    emuk
    -0.07
    è¿Ļç§įçݰ象
    -0.07
    æĿ¯æ°´
    -0.07
    çĥŃ线çĶµè¯Ŀ
    -0.07
    .baidu
    -0.07
    ساÙĨ
    -0.07
    namen
    -0.07
    POSITIVE LOGITS
    åħ³ç³»
    0.08
    ãĢģ
    0.07
     etc
    0.07
    less
    0.07
    elle
    0.07
     relationships
    0.07
     behavior
    0.07
    ä¸įè¦ģå¿ĺäºĨ
    0.07
     relations
    0.07
     and
    0.07
    Activations Density 0.134%

    No Known Activations