© 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. 30509
    Prev
    Next
    INDEX
    Explanations

    clear and direct language

    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
    æĽ´åħ¨
    -0.09
    æĽ´åħ¨éĿ¢
    -0.08
     illegally
    -0.08
    ulk
    -0.07
    æĽ´æ·±åħ¥
    -0.07
    dle
    -0.07
    æĽ´æ·±
    -0.07
    ковÑģкий
    -0.07
    æĪĸåĪłéĻ¤
    -0.07
    为己
    -0.07
    POSITIVE LOGITS
    /simple
    0.09
    ç®Ģæĺİ
    0.09
    ament
    0.08
    åĪ©èIJ½
    0.08
     simple
    0.08
     unkompl
    0.08
    æĪijåĸľæ¬¢
    0.07
    ç®Ģæ´ģ
    0.07
    -simple
    0.07
    ç®Ģä½ĵä¸Ńæĸĩ
    0.07
    Activations Density 0.036%

    No Known Activations