© 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. 45872
    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
    amed
    -0.08
    igent
    -0.08
    unge
    -0.08
    untu
    -0.08
    igrated
    -0.07
    ambo
    -0.07
    akat
    -0.07
    stücke
    -0.07
     mongoose
    -0.07
     jednos
    -0.07
    POSITIVE LOGITS
    ially
    0.07
    æ£Ģ
    0.07
    æĭīæĭī
    0.06
    ippi
    0.06
    ç©į
    0.06
    vest
    0.06
    æĮīçħ§
    0.06
    oriously
    0.06
    &
    0.06
    neu
    0.06
    Activations Density 0.000%

    No Known Activations