© 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. 57990
    Prev
    Next
    INDEX
    Explanations

    mathematical and programming constructs

    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
    leisten
    -0.07
    综åIJĪèĥ½åĬĽ
    -0.07
    饶
    -0.06
    oret
    -0.06
     Gord
    -0.06
    orida
    -0.06
    dn
    -0.06
     lá»iji
    -0.06
    è¡Į
    -0.06
    пп
    -0.06
    POSITIVE LOGITS
    artz
    0.09
     pula
    0.09
    ä»»ä½ķåħ¶ä»ĸ
    0.08
    ä½łéĤ£
    0.08
    almaz
    0.08
    upy
    0.08
    æ´ŀ
    0.08
    èque
    0.07
    åħ¶æŀĹ
    0.07
    omp
    0.07
    Activations Density 0.024%

    No Known Activations