© 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. 20520
    Prev
    Next
    INDEX
    Explanations

    a perspective

    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
    æķı
    -0.07
    beeld
    -0.06
    à¤Ńव
    -0.06
    å¾Ħ
    -0.06
    bic
    -0.06
    ìĩł
    -0.06
    onex
    -0.06
    涼
    -0.06
    FromArray
    -0.05
    ież
    -0.05
    POSITIVE LOGITS
    è¿Ļæĸ¹éĿ¢çļĦ
    0.13
    è¿Ļä¸ĢçĤ¹
    0.12
    è¿Ļä¸ĢéĹ®é¢ĺ
    0.11
    è¿Ļæĸ¹éĿ¢
    0.10
    è¿Ļæł·çļĦéĹ®é¢ĺ
    0.10
    è¿Ļ个éĹ®é¢ĺ
    0.10
    è¿ĻçĤ¹
    0.10
    éĢĻåĢĭåķıé¡Į
    0.09
    æѤ类
    0.09
    éĢĻä¸Ģé»ŀ
    0.09
    Activations Density 0.475%

    No Known Activations