© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 46768
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ¦
    -0.07
    สà¹Īวà¸Ļà¸Ĥà¸Ńà¸ĩ
    -0.07
    _LANGUAGE
    -0.07
    ä»ħæѤ
    -0.07
    ä½łçľĭ
    -0.07
     unjust
    -0.07
    ç½®æį¢
    -0.07
    länd
    -0.06
     juxtap
    -0.06
    æ½¼
    -0.06
    POSITIVE LOGITS
    ationToken
    0.08
    alb
    0.08
    èĶ½
    0.07
    <![
    0.07
    iese
    0.07
    calcul
    0.07
    (/^\
    0.06
    _DATABASE
    0.06
    åIJĮ声
    0.06
    underscore
    0.06
    Activations Density 0.000%

    No Known Activations