© 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. 58832
    Prev
    Next
    INDEX
    Explanations

    noise and errors

    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
    plates
    -0.06
     plates
    -0.06
    ãĤģãģIJ
    -0.06
    ä¸ĵ
    -0.06
    解ç¦ģ
    -0.06
    eut
    -0.06
    ìľ¡
    -0.06
    æĮĤçĿĢ
    -0.06
    iedo
    -0.06
    TON
    -0.06
    POSITIVE LOGITS
    åĻªå£°
    0.09
     ÑĪÑĥма
    0.09
    éļıæľº
    0.09
    .random
    0.09
    aime
    0.09
     noise
    0.09
    random
    0.08
    /errors
    0.08
    даÑĤ
    0.08
     unpredictable
    0.08
    Activations Density 0.007%

    No Known Activations