© 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. 15223
    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
    utine
    -0.08
    ernals
    -0.08
    untlet
    -0.08
    leter
    -0.08
    айд
    -0.08
    erce
    -0.08
    ctp
    -0.08
    anner
    -0.07
    avadoc
    -0.07
    ulton
    -0.07
    POSITIVE LOGITS
    åĿŀ
    0.06
    tha
    0.06
    ke
    0.06
    ç¯ĩä¸Ģ
    0.06
    åijĨ
    0.06
    imba
    0.06
    UE
    0.06
    think
    0.06
    :&
    0.06
    æĹ¥çĶŁ
    0.06
    Activations Density 0.691%

    No Known Activations

    This feature has no known activations.