© 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. 58264
    Prev
    Next
    INDEX
    Explanations

    Russian words, English business terms

    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
    ï¸İ
    -0.08
     tweaked
    -0.08
    raad
    -0.08
    (which
    -0.08
    æĢ»æľīä¸Ģ天
    -0.07
    [@
    -0.07
    æ´ŀå¯Ł
    -0.07
     czÄĻ
    -0.07
    ç»ijå®ļ
    -0.07
    .Timestamp
    -0.07
    POSITIVE LOGITS
     prolong
    0.07
    elts
    0.07
    ikum
    0.07
    olos
    0.06
    oooooooo
    0.06
    å®īçIJª
    0.06
    åľ¨çĶŁäº§
    0.06
    enced
    0.06
    æķĸ
    0.06
    被人们
    0.06
    Activations Density 0.013%

    No Known Activations