© 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. 65086
    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
    æĿ¡æĿ¡
    -0.10
    мелÑĮ
    -0.07
    aan
    -0.07
    emale
    -0.07
    çī¢
    -0.07
    å¹´å¹´åºķ
    -0.07
    ident
    -0.07
    åīįéĢĶ
    -0.07
    æŃ¤èµ·
    -0.07
    erness
    -0.07
    POSITIVE LOGITS
    æĹłèĥ½
    0.07
    eis
    0.07
    ×ķ×Ĵ
    0.07
    _PATTERN
    0.07
    жели
    0.06
    iskon
    0.06
    çĵ®
    0.06
    ESI
    0.06
    åªĴ
    0.06
    ISI
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.