© 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. 61352
    Prev
    Next
    INDEX
    Explanations

    .php, Python, R, conversion

    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
    ç¦Ħ
    -0.07
    è¾ľ
    -0.07
    .opacity
    -0.07
    idt
    -0.07
     Genome
    -0.07
    adge
    -0.07
    è¶ħèĸĦ
    -0.06
     incidental
    -0.06
    ä¼ĺç§ĢçļĦ
    -0.06
    鸳
    -0.06
    POSITIVE LOGITS
    çĿ
    0.09
     Converted
    0.08
    æĿ¥å¾ĹåıĬ
    0.08
    转æį¢
    0.08
     convers
    0.07
    roj
    0.07
    å¥
    0.07
     conversion
    0.07
    转æį¢ä¸º
    0.07
    Convert
    0.07
    Activations Density 0.135%

    No Known Activations