© 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. 25145
    Prev
    Next
    INDEX
    Explanations

    related to concerns

    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
    &R
    -0.07
    ÐľÐķ
    -0.07
    merge
    -0.07
    enam
    -0.07
    lest
    -0.07
     preval
    -0.07
    æľīéĤ£ä¹Ī
    -0.07
     Riau
    -0.07
     chánh
    -0.07
    @hotmail
    -0.07
    POSITIVE LOGITS
     contributes
    0.08
     contribu
    0.08
     contribute
    0.08
     contribution
    0.08
    åıĤä¸İåĪ°
    0.08
     contrib
    0.08
    åĬ©æݨ
    0.07
    æĸ¹éĿ¢çļĦ
    0.07
    åĽłç´łå½±åĵį
    0.07
    å½¢å¼ıçļĦ
    0.07
    Activations Density 0.933%

    No Known Activations