© 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. 781
    Prev
    Next
    INDEX
    Explanations

    `echo` commands

    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
    imum
    -0.07
    ader
    -0.07
    tfoot
    -0.07
    schen
    -0.06
    cury
    -0.06
     frag
    -0.06
    ska
    -0.06
    çĤľ
    -0.06
    uder
    -0.06
    geom
    -0.06
    POSITIVE LOGITS
    αÏģ
    0.08
    alization
    0.07
    loyd
    0.07
    ayne
    0.07
    leston
    0.07
    Äĥm
    0.07
    çĻ½äºĨ
    0.07
    ìĥģìľ¼ë¡ľ
    0.07
    wab
    0.07
    好æĥ³
    0.07
    Activations Density 0.001%

    No Known Activations