© 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. 59000
    Prev
    Next
    INDEX
    Explanations

    not clear or difference

    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
    åıªè¦ģèĥ½
    -0.09
    xAE
    -0.08
    å°ģ
    -0.08
    YW
    -0.07
    nard
    -0.07
    ãĥijãĥ¼ãĥĪãĥĬãĥ¼
    -0.07
    fixture
    -0.07
    mission
    -0.07
    ysl
    -0.07
    éĢļåĪĻ
    -0.07
    POSITIVE LOGITS
    oks
    0.08
     опÑĢеделÑij
    0.08
    ä¸İåĽ½åĨħ
    0.07
    ase
    0.07
    azor
    0.07
    ä¸Ģå®ļ
    0.07
    ouse
    0.07
    ideo
    0.07
    PlainText
    0.06
    éľĦ
    0.06
    Activations Density 0.001%

    No Known Activations