© 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. 41905
    Prev
    Next
    INDEX
    Explanations

    specific word endings

    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
    åīª
    -0.07
     l
    -0.06
     li
    -0.06
    æ±ł
    -0.06
    -0.05
     lo
    -0.05
     labor
    -0.05
    对æµģ
    -0.05
     C
    -0.05
     favor
    -0.05
    POSITIVE LOGITS
    æݸ
    0.09
    Ùĩب
    0.09
     коÑĪе
    0.08
    ä½ľä¸ºåĽ½åĨħ
    0.08
    ẹt
    0.08
    herits
    0.08
    æĪĸåħ¶
    0.08
    大åħ¸
    0.08
    inste
    0.08
    PFN
    0.08
    Activations Density 0.241%

    No Known Activations