© 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. 26086
    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
    ibilit
    -0.07
    ubile
    -0.07
    ±
    -0.07
    enance
    -0.07
    å°Ķ夫
    -0.07
    åĪ©çī©
    -0.07
    æĢĿéĩı
    -0.07
    baÅŁ
    -0.07
    swick
    -0.07
    áī
    -0.07
    POSITIVE LOGITS
    è²Į
    0.08
    rum
    0.08
    aque
    0.08
    çĽ¸ä¼¼æĸĩçĮ®
    0.07
    avers
    0.07
    teres
    0.07
    æ¯ĵ
    0.07
    ä¹Łç½¢
    0.06
    å
    0.06
    exus
    0.06
    Activations Density 0.000%

    No Known Activations