© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 51151
    Prev
    Next
    INDEX
    Explanations

    charges lodged

    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
    ucer
    -0.07
    ilhar
    -0.07
    Äĥn
    -0.07
    amble
    -0.07
    ä¸įå°½
    -0.07
    Zum
    -0.07
    çŁ¢
    -0.06
    夫妻
    -0.06
    éĺ´éĺ³
    -0.06
    ANNER
    -0.06
    POSITIVE LOGITS
    æĿ¥èĩª
    0.08
    åİŁä½ľèĢħ
    0.08
    缸æīĭãģ®
    0.07
    çĶ²æĸ¹çļĦ
    0.07
    yre
    0.07
    ä¾Ĩèĩª
    0.07
    ail
    0.07
    rl
    0.07
     milik
    0.07
    สà¹Īวà¸Ļà¸Ĥà¸Ńà¸ĩ
    0.07
    Activations Density 0.922%

    No Known Activations