© 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. 23697
    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
    ignon
    -0.07
    UMA
    -0.07
    临éŨ
    -0.07
    Intermediate
    -0.06
    &
    -0.06
    if
    -0.06
     neither
    -0.06
    ou
    -0.06
    ä¸įçŁ¥ä¸įè§ī
    -0.06
    æµĭ
    -0.06
    POSITIVE LOGITS
    á´Ľ
    0.08
    .emit
    0.08
    åı¯æ¢¦
    0.08
    綱
    0.08
     prevision
    0.08
    -peer
    0.08
    оек
    0.08
    纲
    0.08
    yaj
    0.08
    ç»·
    0.07
    Activations Density 0.000%

    No Known Activations