© 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. 15231
    Prev
    Next
    INDEX
    Explanations

    cross and intersection shapes

    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
    	trigger
    -0.08
    è¿ijäºĨ
    -0.07
    uraa
    -0.07
    åįĹé£İ
    -0.07
    çĸĨ
    -0.07
    erien
    -0.07
    çĻ¾å·Ŀ
    -0.07
    åį·æĿIJ
    -0.07
    ÑĢил
    -0.07
    goog
    -0.07
    POSITIVE LOGITS
    çĽ¸äº¤
    0.08
    äºĴ缸
    0.08
    à¸ģลาà¸ĩ
    0.08
     intersection
    0.07
    缸äºĴ
    0.07
     Intersection
    0.07
     intersect
    0.07
     intersections
    0.07
    交åıī
    0.07
    å½¼æѤçļĦ
    0.07
    Activations Density 0.004%

    No Known Activations