© 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. 4863
    Prev
    Next
    INDEX
    Explanations

    24 hours

    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
    yé
    -0.09
    pector
    -0.08
    vably
    -0.08
    KET
    -0.08
    mallow
    -0.08
    ioned
    -0.08
    quit
    -0.08
    erial
    -0.08
    ä¹Ŀå¹´
    -0.08
    assi
    -0.08
    POSITIVE LOGITS
    ä¸Ģå¤ľ
    0.07
    çĪ¬èµ·æĿ¥
    0.07
    /day
    0.07
    -day
    0.06
     ÑģÑĥÑĤки
    0.06
    é»ijå¤ľ
    0.06
    åĨħå¤ĸ
    0.06
    odne
    0.06
    izon
    0.06
     overnight
    0.06
    Activations Density 0.047%

    No Known Activations