© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 9059
    Prev
    Next
    INDEX
    Explanations

    overtime pay, interchange fees, rating agencies, education students

    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
    aight
    -0.07
    æīĢæĮĩ
    -0.07
    exus
    -0.07
    åħ·ä½ĵçļĦ
    -0.07
    濯
    -0.06
    elda
    -0.06
    ä¸įä½ıçļĦ
    -0.06
    letcher
    -0.06
    attet
    -0.06
    (Target
    -0.06
    POSITIVE LOGITS
    çŃīä¼łç»Ł
    0.08
    äºĭåħ³
    0.08
    çļĦä¼łç»Ł
    0.08
     traditionally
    0.08
     оÑģÑĤан
    0.07
    管çIJĨä½ĵåĪ¶
    0.07
    æī¿æĭħçĿĢ
    0.07
    ä»ĸç«ŁçĦ¶
    0.07
    å®ģåı¯
    0.07
    åį´ä¾ĿçĦ¶
    0.07
    Activations Density 0.432%

    No Known Activations