© 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. 43270
    Prev
    Next
    INDEX
    Explanations

    Rule of prediction

    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
    .Configuration
    -0.07
    åĬ¨æľº
    -0.07
     imagined
    -0.07
    è¯ĬæĸŃåıĬ
    -0.07
     visited
    -0.07
    Configuration
    -0.07
     insgesamt
    -0.07
     submitted
    -0.06
    æĢ»ä¸įèĥ½
    -0.06
    磼
    -0.06
    POSITIVE LOGITS
    æł¡æŃ£
    0.08
     empir
    0.08
    éĢļçĶ¨
    0.08
    åŁºäºİ
    0.07
    coef
    0.07
     shortcut
    0.07
     handy
    0.07
     constants
    0.07
     коÑįÑĦÑĦиÑĨи
    0.07
    åįķä½į为
    0.07
    Activations Density 0.001%

    No Known Activations