© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 14263
    Prev
    Next
    INDEX
    Explanations

    English translations and code

    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
    éģį
    -0.08
     mauvais
    -0.07
    atric
    -0.07
    æ¯ĶåĪ«äºº
    -0.07
    صÙĬب
    -0.07
    Lon
    -0.06
    cket
    -0.06
    Assembler
    -0.06
    Advertisements
    -0.06
    æĹ©çĿ¡
    -0.06
    POSITIVE LOGITS
    åºĶ该就æĺ¯
    0.07
    ovac
    0.07
    æī«æıı件
    0.06
    ä¸İä¿¡æģ¯
    0.06
    izations
    0.06
     thảo
    0.06
     ×IJ×Ĺ
    0.06
    []"
    0.06
    éĥ½å¸Ĥ
    0.06
    antang
    0.06
    Activations Density 0.002%

    No Known Activations