© 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. 13569
    Prev
    Next
    INDEX
    Explanations

    factors concentration area

    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
    .att
    -0.06
     potentially
    -0.06
    apur
    -0.06
     intersection
    -0.06
    Âł
    -0.06
    漫漫
    -0.06
     intersections
    -0.06
    çļĩ
    -0.06
    çĶļèĩ³æľīäºĽ
    -0.06
    åģ¥åº·å®īåħ¨
    -0.05
    POSITIVE LOGITS
    _PC
    0.11
    è¶Ĭ大
    0.10
     decreases
    0.10
    ä¹Łä¼ļå½±åĵį
    0.10
    亦çĦ¶
    0.09
    å¢ŀ大
    0.09
    缴æݥ影åĵį
    0.09
    åĽłç´ł
    0.09
    è¶Ĭ强
    0.09
     factors
    0.09
    Activations Density 0.055%

    No Known Activations