© 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. 23574
    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
    ål
    -0.09
    ylon
    -0.08
     Hierzu
    -0.08
    é£İèµ·
    -0.07
    èĭ¦ç»ĥ
    -0.07
    籤
    -0.07
    ös
    -0.07
    odia
    -0.07
    æĹ¥æĻļ
    -0.07
    ä¿¡åı·çļĦ
    -0.07
    POSITIVE LOGITS
     calor
    0.09
     heat
    0.09
    åįĩ温
    0.08
    heat
    0.08
    Heat
    0.08
    表ä¸Ń
    0.08
     нагÑĢе
    0.08
     thermal
    0.08
     absor
    0.08
     Heat
    0.08
    Activations Density 0.000%

    No Known Activations