© 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. 41371
    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
    ulas
    -0.08
    af
    -0.08
    åĶĩ
    -0.07
    stab
    -0.07
    æµ®
    -0.07
     incis
    -0.07
     Watkins
    -0.07
    аем
    -0.06
    åĮħåĽ´
    -0.06
    èį¯æ°´
    -0.06
    POSITIVE LOGITS
    opal
    0.07
    иÑĢо
    0.07
    λλ
    0.07
    西游
    0.06
    æŃ
    0.06
    bior
    0.06
    åIJı
    0.06
    mera
    0.06
    αιο
    0.06
    åĩĮ空
    0.06
    Activations Density 0.000%

    No Known Activations