© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 58961
    Prev
    Next
    INDEX
    Explanations

    constructor, method, or type signatures

    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
    Negative Logits
    è¶ĭ
    -0.08
    lesson
    -0.08
    luft
    -0.07
    lessons
    -0.07
    åѦä¼ļäºĨ
    -0.07
    £¼
    -0.07
    ongi
    -0.07
    åѦåĪ°äºĨ
    -0.07
    ilos
    -0.06
    imbus
    -0.06
    POSITIVE LOGITS
    å®ī迪
    0.08
    æīİåħĭ
    0.07
    ä¸īéĩĮ
    0.07
     legacy
    0.07
     Legacy
    0.07
     synonyms
    0.06
    berg
    0.06
     Oral
    0.06
     vari
    0.06
    deprecated
    0.06
    Activations Density 0.044%

    No Known Activations