© 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. 47787
    Prev
    Next
    INDEX
    Explanations

    rotation and movement

    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
    volver
    -0.07
     пÑĢиÑģÑĤ
    -0.07
    è¿Ļç§įåģļæ³ķ
    -0.07
    -inline
    -0.07
    niÄį
    -0.07
    ardan
    -0.07
    æĢ»çļĦ
    -0.06
    áĢ±áĢ¬
    -0.06
     hoãn
    -0.06
    inton
    -0.06
    POSITIVE LOGITS
    urge
    0.07
    ä¸İåIJ¦
    0.07
     normally
    0.07
    çĬ¶æĢģä¸ĭ
    0.07
     action
    0.07
    åĸľæĤ¦
    0.07
    åĴĮä½ľçĶ¨
    0.07
    dg
    0.06
    iewicz
    0.06
    ead
    0.06
    Activations Density 0.132%

    No Known Activations