© 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. 57470
    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
    uin
    -0.08
    roma
    -0.08
    зд
    -0.07
     crossorigin
    -0.07
     maur
    -0.07
    æľ¬
    -0.07
    imilar
    -0.07
    -dir
    -0.07
    æ·ij
    -0.07
    èĺĭ
    -0.07
    POSITIVE LOGITS
    ocha
    0.07
    æľīæѤ
    0.06
    {}_
    0.06
    泡
    0.06
    _FF
    0.06
    CLI
    0.06
    LAG
    0.06
     Suff
    0.06
    åij¦
    0.06
     sacrifices
    0.06
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.