© 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. 42321
    Prev
    Next
    INDEX
    Explanations

    in terms of

    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
    ä¸Ģ个
    -0.08
    太éĥİ
    -0.07
    /utility
    -0.07
    entai
    -0.07
    alama
    -0.07
    åĩºäºİ
    -0.07
    htub
    -0.07
    å©
    -0.07
     reta
    -0.06
    æŁIJ
    -0.06
    POSITIVE LOGITS
     terms
    0.10
    attet
    0.08
    å¦Ĥä¸ĭ
    0.08
    åĬŀç¨İ
    0.07
    çĶµè®¯
    0.07
    oween
    0.07
    书éĿ¢å½¢å¼ı
    0.07
    èĴ²
    0.07
    mour
    0.07
    forma
    0.07
    Activations Density 0.024%

    No Known Activations