© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 59969
    Prev
    Next
    INDEX
    Explanations

    for example

    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
    Negative Logits
    çļĦ天çĦ¶
    -0.07
    çĽ¸ä¼¼æĸĩçĮ®
    -0.07
    elia
    -0.07
     поÑģÑĭ
    -0.07
    yth
    -0.07
    aina
    -0.07
    thal
    -0.07
    /problems
    -0.06
     governments
    -0.06
     веÑĩ
    -0.06
    POSITIVE LOGITS
     reportedly
    0.09
    æĽ´çĶŁ
    0.07
    éĻĮ
    0.07
    åħ·ä½ĵçļĦ
    0.07
    è§Ħå®ļ
    0.07
    erox
    0.07
     specifics
    0.07
    éĽ¯
    0.07
    ãĤ´ãĥ¼ãĥ«ãĥĩãĥ³
    0.07
    °
    0.06
    Activations Density 0.048%

    No Known Activations