© 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. 15043
    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
     Fond
    -0.08
    è¡ħ
    -0.08
    ancellable
    -0.07
    byname
    -0.07
    chl
    -0.07
    åĢ¾
    -0.07
    æľī趣çļĦæĺ¯
    -0.07
    åİŁä½į
    -0.07
    apers
    -0.07
    æī¹åĩĨ
    -0.07
    POSITIVE LOGITS
     تغ
    0.08
    -plugin
    0.07
    agog
    0.07
    代
    0.07
    sig
    0.06
    imo
    0.06
    Öģ
    0.06
     feeding
    0.06
    à¨ħ
    0.06
    esis
    0.06
    Activations Density 0.000%

    No Known Activations