© 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. 40581
    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
    -hooks
    -0.08
    åĬłåħ³æ³¨
    -0.07
    æ¸ī
    -0.07
    被æµıè§Ī
    -0.07
    ayar
    -0.06
     Marca
    -0.06
    +offset
    -0.06
    æĮ¨
    -0.06
    atorie
    -0.06
    .hasClass
    -0.06
    POSITIVE LOGITS
    mage
    0.08
    èĩ»
    0.08
    pta
    0.07
    åħīèį£
    0.07
    åĽ
    0.07
    家ä¼Ļ
    0.07
    çļĦæľĢç»Ī
    0.06
    áĢº
    0.06
    ç¥ŀçĪ¶
    0.06
    交æµģåIJĪä½ľ
    0.06
    Activations Density 0.000%

    No Known Activations