© 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. 65102
    Prev
    Next
    INDEX
    Explanations

    increment/decrement operators

    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
    ijo
    -0.09
    è¿Ľä¸ĢæŃ¥æī©å¤§
    -0.08
    è¿ĻäºĽä¿¡æģ¯
    -0.07
    è¾ĥ强
    -0.07
    heids
    -0.07
    ite
    -0.07
    omé
    -0.07
    ugging
    -0.07
    ìĸ´ë²Ħ
    -0.07
    embra
    -0.07
    POSITIVE LOGITS
    AndGet
    0.09
    ìĶ©
    0.08
    缴èĩ³
    0.07
    ully
    0.07
    uce
    0.07
    ute
    0.07
    блÑİ
    0.07
     marche
    0.06
    çµ
    0.06
    .PI
    0.06
    Activations Density 0.027%

    No Known Activations