© 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. 31823
    Prev
    Next
    INDEX
    Explanations

    Museum exhibition

    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
    å¤įä¹łèµĦæĸĻ
    -0.07
    -gnu
    -0.07
    çł´çĥĤ
    -0.07
    edom
    -0.07
    -original
    -0.07
    å¢ĥå¤ĸè¾ĵåħ¥
    -0.07
    lsa
    -0.07
    «
    -0.07
    åı¯ä»¥ç»Ļ
    -0.07
     Apartments
    -0.06
    POSITIVE LOGITS
    泡
    0.07
    éħ
    0.07
    باس
    0.06
    acea
    0.06
    waard
    0.06
     маÑģÑģ
    0.06
    اÙĨØ©
    0.06
     Emb
    0.06
    ç¥ĸæ¯į
    0.06
    \Annotation
    0.06
    Activations Density 0.006%

    No Known Activations