© 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. 11971
    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
    erman
    -0.08
    ocop
    -0.08
    onders
    -0.08
     rued
    -0.08
    å·¥ä½ľçļĦåIJĮæŶ
    -0.08
    aro
    -0.08
    trup
    -0.08
    ogle
    -0.07
    æľ¬æ³ķ
    -0.07
     Wow
    -0.07
    POSITIVE LOGITS
    £¼
    0.07
     spoken
    0.07
    çĵ£
    0.07
    _REGEX
    0.06
    heits
    0.06
    è´¢ç»ı
    0.06
     offline
    0.06
    èļĮ
    0.06
    å¿ĥéĩĮ
    0.06
    çĵ¢
    0.06
    Activations Density 0.000%

    No Known Activations