© 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. 57798
    Prev
    Next
    INDEX
    Explanations

    geometric shapes and dimensions

    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
    çĶ»çļĦ
    -0.08
    å¾ģ
    -0.08
     cres
    -0.08
    æģ¬
    -0.08
    ä¸Ģå¼łå¼ł
    -0.08
    çķ«
    -0.08
     Canvas
    -0.08
    çĶ»
    -0.08
    åĩ°
    -0.08
    urve
    -0.07
    POSITIVE LOGITS
    ä¸īç»´
    0.19
    ç«ĭä½ĵ
    0.16
    åĽĽç»´
    0.13
    ç«ĭé«Ķ
    0.13
    å¤ļç»´
    0.12
    cube
    0.12
     cube
    0.12
    ä½ĵ积
    0.12
     Cube
    0.11
    Cube
    0.11
    Activations Density 0.184%

    No Known Activations