© 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. 51898
    Prev
    Next
    INDEX
    Explanations

    RIGHT movements

    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
    bon
    -0.07
    ä¸İåħ±
    -0.06
    ãģľ
    -0.06
    åĩºåıij
    -0.06
    è¾¼ãģ¿
    -0.06
    å¾·åįİ
    -0.06
    otropic
    -0.06
    è¦Ĩ
    -0.06
    çIJĨè®ºçŁ¥è¯Ĩ
    -0.05
    Joint
    -0.05
    POSITIVE LOGITS
    yton
    0.09
    ynos
    0.08
    ä¸įå¾Ĺå·²
    0.08
    å¿ĥæľī
    0.08
    ankind
    0.08
    emouth
    0.07
    ikia
    0.07
    stash
    0.07
    çļĦä¸Ģç¯ĩ
    0.07
    éĥ¨å°±
    0.07
    Activations Density 0.001%

    No Known Activations