© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17710
    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
    azzi
    -0.06
    orie
    -0.06
    ÙĪ
    -0.06
    ä¸Ńåħ¬
    -0.06
     Gaz
    -0.06
    ells
    -0.06
    段
    -0.05
     disob
    -0.05
    issy
    -0.05
    ell
    -0.05
    POSITIVE LOGITS
    upes
    0.09
    æĪĸåħ¶
    0.09
    UTA
    0.09
    ÏĦÏī
    0.08
    æĽ¿ä½ł
    0.08
    .classes
    0.08
    atina
    0.08
    odik
    0.08
    itera
    0.08
    èĨ³
    0.07
    Activations Density 0.129%

    No Known Activations