© 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. 11379
    Prev
    Next
    INDEX
    Explanations

    asking questions, describing situations

    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
    amt
    -0.07
    夫
    -0.07
    engel
    -0.06
    çļĦ身影
    -0.06
     exp
    -0.06
     Exp
    -0.06
    ÑĢк
    -0.06
    anson
    -0.06
    æĢİä¹ĪéĢī
    -0.06
     mean
    -0.06
    POSITIVE LOGITS
    æŁIJ
    0.11
    æĪĸæľįåĬ¡
    0.10
    æĪĸå¤ļ个
    0.09
    æĸĩ件æĪĸ
    0.09
    enant
    0.09
    æīĢ欲
    0.09
    æĪĸåħ¶
    0.09
    æŁIJ个
    0.09
    utzen
    0.09
    å·¥ä½ľæĪĸ
    0.09
    Activations Density 0.133%

    No Known Activations