© 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. 58330
    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
    ç½®
    -0.07
    yczy
    -0.07
    失èIJ½
    -0.07
    絡
    -0.07
     gradu
    -0.07
     influ
    -0.07
    åĪĨæĺİ
    -0.06
    èѬå¦Ĥ
    -0.06
    å½±åĵįåĽłç´ł
    -0.06
    ermen
    -0.06
    POSITIVE LOGITS
    å±±ä¹ĭ
    0.07
    婪
    0.07
    -&
    0.07
    ä¹ĭæīį
    0.07
    à¸Ĭัย
    0.06
    &R
    0.06
    并ä¸įéļ¾
    0.06
    ç¿İ
    0.06
    ä¸įæĦ§
    0.06
     failed
    0.06
    Activations Density 0.000%

    No Known Activations