© 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. 44465
    Prev
    Next
    INDEX
    Explanations

    letter openings and closings

    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
     basically
    -0.08
     freaking
    -0.08
     busty
    -0.08
     gee
    -0.08
    å·ĿæĻ®
    -0.07
     supposedly
    -0.07
    èĥľ
    -0.07
     mans
    -0.07
    å§ĭèĩ³
    -0.07
    ocab
    -0.07
    POSITIVE LOGITS
     myself
    0.08
    æĥħå½¢
    0.08
    使æĪij
    0.08
    bestand
    0.07
    çļĦæĥħå½¢
    0.07
     terci
    0.07
    yb
    0.07
    äºĭåĬ¡
    0.07
     trif
    0.06
    ä¸Ģå®ļä¸įèĥ½
    0.06
    Activations Density 0.019%

    No Known Activations