© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 16763
    Prev
    Next
    INDEX
    Explanations

    record or ratio

    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
    WithValue
    -0.08
    kez
    -0.08
    trinsic
    -0.08
    oca
    -0.08
    çĶ¨æĪ·åı¯ä»¥
    -0.07
    kilde
    -0.07
    licit
    -0.07
    ivi
    -0.07
    quil
    -0.07
     endowed
    -0.07
    POSITIVE LOGITS
     ratios
    0.10
    æ¯Ķä¾ĭ为
    0.10
     ratio
    0.10
    æ¯Ķä¾ĭ
    0.09
     outcomes
    0.09
    Ratio
    0.09
    æ¯Ķä¾ĭçļĦ
    0.09
     proportions
    0.09
     percentages
    0.08
     segreg
    0.08
    Activations Density 0.003%

    No Known Activations