© 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. 7292
    Prev
    Next
    INDEX
    Explanations

    processes or reactions involved

    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
    éĵ¶å±±
    -0.08
    istre
    -0.07
    gage
    -0.07
     Struk
    -0.07
    çĪ¶å¥³
    -0.07
    raphe
    -0.07
    ắn
    -0.07
     ovunque
    -0.07
    estin
    -0.07
    erlo
    -0.07
    POSITIVE LOGITS
    åıĤä¸İçļĦ
    0.09
    åıĤä¸İ
    0.08
     available
    0.08
     задей
    0.08
     mixing
    0.08
     Available
    0.08
    available
    0.07
    æ··ãģľ
    0.07
    èŀįåIJĪçļĦ
    0.07
    åıĤä¸İåĪ°
    0.07
    Activations Density 0.001%

    No Known Activations