© 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. 47128
    Prev
    Next
    INDEX
    Explanations

    compression, encoding, lzham

    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
     Äįl
    -0.07
    enha
    -0.07
    æ¸ħçIJĨå¹²åĩĢ
    -0.07
     spur
    -0.07
    ç¼ĺåĪĨ
    -0.06
    线ä¸ĬçļĦ
    -0.06
    asy
    -0.06
    leck
    -0.06
    ä¸įéĢĢ
    -0.06
    ipation
    -0.06
    POSITIVE LOGITS
     encoding
    0.08
    imitives
    0.08
     tape
    0.08
    ç¼ĸçłģ
    0.08
     Vatic
    0.08
    æ¦Ĥæĭ¬
    0.08
    /ss
    0.08
     poup
    0.07
    å°ıèĥĸ
    0.07
     redund
    0.07
    Activations Density 0.015%

    No Known Activations