© 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. 13327
    Prev
    Next
    INDEX
    Explanations

    mathematical or logical operators

    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
    etta
    -0.08
    ibar
    -0.07
    ÙħÙĬØ©
    -0.07
     bl
    -0.07
    ỡ
    -0.06
    æĸ°åĬłåĿ¡
    -0.06
    dek
    -0.06
    å¦ĤåIJĮä¸Ģ
    -0.06
    Õ»
    -0.06
    amakan
    -0.06
    POSITIVE LOGITS
    æ¨
    0.09
    .appspot
    0.08
    åħ¬èĭ±
    0.07
    hil
    0.07
    ç¤İ
    0.07
     ÙħÙĨاط
    0.07
    yai
    0.07
    åįĥåįĥ
    0.07
    -scripts
    0.07
    ül
    0.07
    Activations Density 0.028%

    No Known Activations