© 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. 21805
    Prev
    Next
    INDEX
    Explanations

    for loop iteration

    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
    em
    -0.07
     collectively
    -0.06
    extra
    -0.06
    /
    -0.06
    ä¸Ģ段æŶéĹ´åIJİ
    -0.06
    è´°
    -0.06
     Sap
    -0.06
    uka
    -0.06
    endo
    -0.06
    prefer
    -0.06
    POSITIVE LOGITS
    FromArray
    0.08
    移åĬ¨çīĪ
    0.08
     tiks
    0.08
    astia
    0.07
    _MSK
    0.07
    é®®
    0.07
    æķ´ä¸ªäºº
    0.07
    -fill
    0.07
    htub
    0.07
    _SCL
    0.07
    Activations Density 0.015%

    No Known Activations