© 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. 34700
    Prev
    Next
    INDEX
    Explanations

    2D plane objects

    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
    uber
    -0.08
     cube
    -0.08
    è©°ãĤģ
    -0.08
    cube
    -0.07
    Cube
    -0.07
    .Deep
    -0.07
    Ñħам
    -0.07
    ÃĶN
    -0.07
    åħļåĴĮ人æ°ij
    -0.07
     cubes
    -0.07
    POSITIVE LOGITS
    ä¸¤å¼ł
    0.09
    ç»ĺåĪ¶
    0.09
    åĽ¾æ¡Ī
    0.09
    å¹³éĿ¢åĽ¾
    0.09
    ceau
    0.09
    éĿ¢ç§¯çļĦ
    0.08
    éĿ¢ç§¯
    0.08
    ä¸¤äººåľ¨
    0.08
    -plane
    0.08
    éĿ¢ç§¯ä¸º
    0.08
    Activations Density 0.040%

    No Known Activations