© 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. 22256
    Prev
    Next
    INDEX
    Explanations

    non-

    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
    缴æİ¥æĪĸéĹ´æİ¥
    -0.08
     Confidential
    -0.07
    åĩ¡äºĭ
    -0.07
    çĤ¹è¿Ľè¡Į
    -0.07
    åłĤ
    -0.07
     confidential
    -0.07
    æī§è¡Į人
    -0.07
     Independ
    -0.07
    æĪĸèĢħåħ¶ä»ĸ
    -0.07
    ripe
    -0.07
    POSITIVE LOGITS
     neither
    0.11
     Neither
    0.08
    è¿ĺæĺ¯ä¸į
    0.08
    æĹ¢ä¸į
    0.08
    Neither
    0.08
     sprawling
    0.08
     zwar
    0.07
    è¿ĺæĺ¯ä¸įéĶĻçļĦ
    0.07
     ÙĪغÙĬر
    0.07
    æĪijä¸įæĺ¯
    0.07
    Activations Density 0.005%

    No Known Activations