© 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. 12720
    Prev
    Next
    INDEX
    Explanations

    final stage or completion

    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
    åħĪè¡Į
    -0.07
    å§ĭ建äºİ
    -0.07
    çİ°åľ¨å·²ç»ı
    -0.07
    åĽºæľīçļĦ
    -0.07
    åİĨæĿ¥
    -0.07
    _OLD
    -0.06
    abor
    -0.06
    uddin
    -0.06
    å½ĵä¸ĭçļĦ
    -0.06
    achen
    -0.06
    POSITIVE LOGITS
     nanti
    0.13
     final
    0.11
    -final
    0.10
    final
    0.10
    æľĢç»Ī
    0.10
     اÙĦÙĨÙĩائÙĬ
    0.10
     result
    0.09
     اÙĦÙĨÙĩائÙĬØ©
    0.09
    ç»ĵæŀľ
    0.09
     akhir
    0.09
    Activations Density 0.085%

    No Known Activations