© 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. 46485
    Prev
    Next
    INDEX
    Explanations

    biological and technical terms

    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
    issy
    -0.08
     Heid
    -0.08
    plode
    -0.08
    _suite
    -0.07
    å®Ŀåħ¸
    -0.07
    клей
    -0.07
    éĵģé¾Ļ
    -0.07
    ศิ
    -0.07
    çī¹æ®ĬæĢ§
    -0.07
    buat
    -0.07
    POSITIVE LOGITS
    离
    0.08
    cert
    0.07
    omore
    0.07
    éĽ¢
    0.06
    ç»ıåħ¸
    0.06
    esel
    0.06
    éĩijåĪļ
    0.06
    èĬĿ
    0.06
    ä¸ĬéŨ
    0.06
    æĬ
    0.06
    Activations Density 0.900%

    No Known Activations