© 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. 34213
    Prev
    Next
    INDEX
    Explanations

    geometric intersection

    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
    åįķä½įåĴĮ个人
    -0.07
    .Microsoft
    -0.07
     Tw
    -0.07
    .substr
    -0.06
     surrounded
    -0.06
    \xaa
    -0.06
    对ä¸Ģ个
    -0.06
    ãģ£ãģ±
    -0.06
    说è¯Ŀ
    -0.06
    akt
    -0.06
    POSITIVE LOGITS
     intersect
    0.15
     intersects
    0.14
    intersect
    0.13
     intersection
    0.12
     Intersection
    0.11
     intersections
    0.11
    intersection
    0.11
     пеÑĢеÑģе
    0.10
    Intersection
    0.09
    çĽ¸äº¤
    0.09
    Activations Density 0.037%

    No Known Activations