© 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. 57920
    Prev
    Next
    INDEX
    Explanations

    foreign characters or punctuation

    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
    å°±åı¯ä»¥äºĨ
    -0.08
    AMI
    -0.08
    ä¸Ģå®ļä¸įä¼ļ
    -0.08
    çĪĽ
    -0.07
    讹
    -0.07
    oho
    -0.07
    大åĪ©
    -0.07
    ç£Ĭ
    -0.07
    åıijæĮ¥åĩº
    -0.07
    è¿ĺæĺ¯æ¯Ķè¾ĥ
    -0.07
    POSITIVE LOGITS
    è¿ĿåıįäºĨ
    0.10
    ä¸įåı¯éģ¿åħį
    0.09
     unavoid
    0.09
    ä¸įåı¯éģ¿åħįåľ°
    0.09
    ä½Ĩåıªè¦ģ
    0.09
    ä¸įåı¯éģ¿åħįçļĦ
    0.09
    è¿Ŀåıį
    0.09
    æĢİä¹ĪåĬŀ
    0.08
     violates
    0.08
    éļ¾åħį
    0.08
    Activations Density 0.059%

    No Known Activations