© 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. 601
    Prev
    Next
    INDEX
    Explanations

    questions and discussions

    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
    igno
    -0.06
    omes
    -0.06
    olib
    -0.06
    Æł
    -0.06
    äºĨä¸Ģæł·
    -0.06
    æľīçļĦæŶåĢĻ
    -0.06
    ÐļС
    -0.06
    ammel
    -0.06
    对æĸ¹å½ĵäºĭ人
    -0.06
    ×Ļ×Ķ
    -0.06
    POSITIVE LOGITS
    ï¸
    0.08
    æv
    0.07
    .CG
    0.07
    主é¢ĺæĺ¯
    0.07
    _CTX
    0.07
    ÑĢеб
    0.07
    iska
    0.07
    urm
    0.07
    timeout
    0.07
    åĨħ容æĺ¯
    0.07
    Activations Density 0.347%

    No Known Activations