© 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. 24393
    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
    ä¹ĭæģĭ
    -0.07
    ãģij
    -0.07
    ger
    -0.07
    йд
    -0.06
    æľķ
    -0.06
    modified
    -0.06
    YL
    -0.06
     conce
    -0.06
     Disc
    -0.06
    ÎŃα
    -0.06
    POSITIVE LOGITS
    anner
    0.08
    ám
    0.07
    /dist
    0.07
    éĸ£
    0.07
    hill
    0.07
    æľĢ大åĮĸ
    0.07
    illos
    0.07
    è¿ĻèĤ¡
    0.07
     slan
    0.07
    åħ¬ä¿¡
    0.07
    Activations Density 0.000%

    No Known Activations