© 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. 27974
    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
     admittedly
    -0.08
    αι
    -0.07
     übrigens
    -0.07
    åľ¨è¿Ļæĸ¹éĿ¢
    -0.07
     hopefully
    -0.07
    itere
    -0.07
    aits
    -0.07
    trat
    -0.07
    trand
    -0.06
    çĹ£
    -0.06
    POSITIVE LOGITS
    ä¿IJ
    0.06
    uty
    0.06
    oci
    0.06
    æĮĿ
    0.06
    uming
    0.06
    acán
    0.06
     länge
    0.06
    âĢij
    0.06
    .Protocol
    0.06
    odal
    0.06
    Activations Density 0.000%

    No Known Activations