© 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. 37768
    Prev
    Next
    INDEX
    Explanations

    distribution, limit, statistical

    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
    åĬ²
    -0.07
    æ´ģ
    -0.07
    ugna
    -0.07
    insk
    -0.07
    angs
    -0.07
     slav
    -0.07
     اÙĦØ«ÙĤ
    -0.07
    èĥ½æºIJ
    -0.06
     abd
    -0.06
    æľĶ
    -0.06
    POSITIVE LOGITS
     conditioned
    0.07
    è°ĥæķ´åIJİ
    0.07
    /boot
    0.07
     assumed
    0.07
    fit
    0.07
    -stats
    0.07
    -know
    0.07
    uzu
    0.06
    /stat
    0.06
    çŁ¥éģĵäºĨ
    0.06
    Activations Density 0.008%

    No Known Activations