© 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. 20317
    Prev
    Next
    INDEX
    Explanations

    structural and alterations

    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
    ted
    -0.07
    bard
    -0.07
    ataka
    -0.07
    antik
    -0.07
     lùi
    -0.07
    uada
    -0.06
    æĽ¾ç»ı说è¿ĩ
    -0.06
     tent
    -0.06
    ç¿°
    -0.06
    å¤ļæĸ¹
    -0.06
    POSITIVE LOGITS
    ç»ĵæŀĦ
    0.13
     structure
    0.12
    ç»ĵæŀĦåĴĮ
    0.12
    ç»ĵæŀĦä¸İ
    0.12
    ç»ĵæŀĦçļĦ
    0.12
     structural
    0.12
    structural
    0.11
    structure
    0.11
     Structure
    0.11
    æ§ĭéĢł
    0.11
    Activations Density 0.154%

    No Known Activations