© 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. 47500
    Prev
    Next
    INDEX
    Explanations

    mice, disease, later

    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
    åħ·æľī以ä¸ĭ
    -0.11
    çļĦåIJĹ
    -0.08
    tober
    -0.08
    æĺ¯åIJĹ
    -0.08
     (âĢ¦)
    -0.08
    称
    -0.07
    æ¯Ľæ³½ä¸ľæĢĿæĥ³
    -0.07
    æĢİä¹ĪåĬŀ
    -0.07
    rensa
    -0.07
     пÑĢиÑĩ
    -0.07
    POSITIVE LOGITS
    é£İåIJ¹è¿ĩ
    0.07
     Gib
    0.07
    лив
    0.06
     tied
    0.06
     aba
    0.06
     rein
    0.06
    éĽ¨éľ²
    0.06
    åĿĤ
    0.06
    åIJİæĿ¥çļĦ
    0.06
    ët
    0.06
    Activations Density 0.065%

    No Known Activations