© 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. 15613
    Prev
    Next
    INDEX
    Explanations

    fallback options

    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
    igit
    -0.08
    pixel
    -0.07
    ResponseBody
    -0.07
    elius
    -0.07
    åѦçĶŁåŃ¦ä¹ł
    -0.07
    éĿ¡
    -0.07
    _Off
    -0.06
    мого
    -0.06
    osting
    -0.06
    æ±°
    -0.06
    POSITIVE LOGITS
     recourse
    0.10
     alternatives
    0.09
    ä¸įå¾Ĺå·²
    0.09
    fallback
    0.09
    æĢİä¹ĪåĬŀ
    0.09
    åıªå¥½
    0.09
     alternative
    0.09
    çļĦåħ¶ä»ĸ
    0.09
     resort
    0.09
     fallback
    0.09
    Activations Density 0.114%

    No Known Activations