© 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. 54979
    Prev
    Next
    INDEX
    Explanations

    contrasting options, exceptions

    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
    aza
    -0.07
    uchu
    -0.07
    macher
    -0.06
    à¸Ńาà¸Ķ
    -0.06
    ammel
    -0.06
    attach
    -0.06
    ctor
    -0.06
    elles
    -0.06
    asaki
    -0.06
    angkat
    -0.06
    POSITIVE LOGITS
    ç½¹
    0.08
    å§ĭèĩ³
    0.08
    Matchers
    0.07
    irmed
    0.07
    å¾Ĺèµ·
    0.07
    hra
    0.07
    ç®Ģ书
    0.07
    raction
    0.07
    irm
    0.07
     indeed
    0.07
    Activations Density 0.242%

    No Known Activations