© 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. 10644
    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
    eu
    -0.08
    izzi
    -0.08
    -0.08
    us
    -0.07
    à¸ķà¹Īาà¸ĩ
    -0.07
    å§ĶåĨħ
    -0.07
    çļĦ主
    -0.06
    ambar
    -0.06
    ÂŃ
    -0.06
    aal
    -0.06
    POSITIVE LOGITS
    ardy
    0.08
    IGE
    0.08
    ÙĩراÙĨ
    0.07
     sanz
    0.07
    íĪ¬
    0.07
    ä½łå¥½
    0.07
     пÑĢиобÑĢеÑĤа
    0.07
    icznym
    0.07
    .createCell
    0.06
    ×ķר×Ķ
    0.06
    Activations Density 0.000%

    No Known Activations