© 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. 60039
    Prev
    Next
    INDEX
    Explanations

    pizza

    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
    çª
    -0.07
    èĩªçĦ¶èĢĮ
    -0.07
    acks
    -0.06
    ibel
    -0.06
    以为
    -0.06
    祺
    -0.06
     damn
    -0.06
    sob
    -0.06
    å§ĵåIJį
    -0.06
     fuck
    -0.06
    POSITIVE LOGITS
    AndPassword
    0.09
    ergic
    0.08
    ()._
    0.08
    rijk
    0.08
    omics
    0.07
    ฯ
    0.07
    æ¯ıåħ¬æĸ¤
    0.07
    liny
    0.07
    lehem
    0.07
    zinho
    0.07
    Activations Density 0.006%

    No Known Activations