© 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. 46787
    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
     overlooked
    -0.07
     propag
    -0.07
     dot
    -0.06
    Overall
    -0.06
    en
    -0.06
    èĤĨ
    -0.06
    æĭĤ
    -0.06
    ens
    -0.06
    ento
    -0.06
    Unchecked
    -0.06
    POSITIVE LOGITS
     cáºŃn
    0.08
    ×IJ×Ļ×Ŀ
    0.08
    ardown
    0.08
    æĹı人
    0.08
    .bs
    0.07
    DirectoryName
    0.07
    ä¸ŃåĽ½å®¶
    0.07
     подко
    0.07
    è¿ŀäºij
    0.07
    ulina
    0.07
    Activations Density 0.000%

    No Known Activations