© 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. 59125
    Prev
    Next
    INDEX
    Explanations

    rule book says

    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
    å¬
    -0.08
    空港
    -0.07
    stå
    -0.07
    noop
    -0.07
    pbs
    -0.07
    å¸Ī表
    -0.07
    oso
    -0.06
    bservice
    -0.06
    ึà¸ĩ
    -0.06
    ÙĪÙħØ©
    -0.06
    POSITIVE LOGITS
    olan
    0.08
    RegularExpression
    0.07
    roe
    0.07
    ä»ĺãģį
    0.07
    alled
    0.07
    å¼ķ以为
    0.06
    ãģĤãģı
    0.06
    “
    0.06
    ÑĪев
    0.06
    otal
    0.06
    Activations Density 0.001%

    No Known Activations