© 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. 12574
    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
    æĹłæģĻ
    -0.09
    ÙĦÙĬÙħ
    -0.08
    åĭĴæĸ¯
    -0.08
    ambul
    -0.08
    Ī¬
    -0.08
    bler
    -0.08
    ÑĢек
    -0.08
    ä¸ĩä¸ĩ
    -0.08
    ocker
    -0.08
    ;text
    -0.08
    POSITIVE LOGITS
    erti
    0.06
    计ç®Ĺæľºè½¯ç¡¬ä»¶
    0.06
    èĮ´
    0.06
    设计åĩº
    0.06
    fx
    0.06
     fl
    0.06
    ouden
    0.06
    ERRU
    0.06
     G
    0.06
    s
    0.05
    Activations Density 0.000%

    No Known Activations