© 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. 14428
    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
    ocat
    -0.08
    otov
    -0.07
    å¤ļæĥħ
    -0.07
    oint
    -0.07
    æĸĩçIJĨ
    -0.07
    شر
    -0.07
    ÏĮÏĦε
    -0.07
    _validator
    -0.07
    身åīį
    -0.07
    à¯Īயà¯Ī
    -0.06
    POSITIVE LOGITS
    pressor
    0.07
    åħħåĪĨè°ĥåĬ¨
    0.07
    ndl
    0.07
    marine
    0.07
    UILT
    0.06
    åıijåĪ°
    0.06
    STANCE
    0.06
    åĭķåĬĽ
    0.06
    rafa
    0.06
    æľīç¦ı
    0.06
    Activations Density 0.000%

    No Known Activations