© 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. 55233
    Prev
    Next
    INDEX
    Explanations

    definition or description

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ÛķÚ©
    -0.08
    åĪ°è¿ĩ
    -0.07
    uary
    -0.07
    ting
    -0.07
    ning
    -0.07
    +xml
    -0.07
    atge
    -0.07
    ymology
    -0.07
    éĩıå°ij
    -0.07
    bourg
    -0.06
    POSITIVE LOGITS
    aque
    0.07
     chodzi
    0.07
    oft
    0.07
    ç¦ıåĪ©
    0.06
    ylv
    0.06
    armac
    0.06
    éné
    0.06
    ook
    0.06
    ä¹ĭåĪĥ
    0.06
    affiliate
    0.06
    Activations Density 0.002%

    No Known Activations