© 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. 42258
    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
    ÙĨب
    -0.07
    ç½®
    -0.07
     subjects
    -0.07
    subjects
    -0.07
     Patton
    -0.06
    threat
    -0.06
    aley
    -0.06
    rier
    -0.06
    å¨ģèĥģ
    -0.06
     threat
    -0.06
    POSITIVE LOGITS
    bara
    0.08
    abah
    0.07
    æľķ
    0.07
     Minds
    0.07
     intentionally
    0.07
    Ïĩεί
    0.07
    è¯Ĩ
    0.07
    arness
    0.07
    æĸĽ
    0.07
    ç´¢èı²
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.