© 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. 1505
    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
    alse
    -0.08
    鼷æĸ¯
    -0.06
    æķ¬ä¸ļ
    -0.06
    åIJİ继
    -0.06
    üp
    -0.06
    /activity
    -0.06
    ledi
    -0.06
    缮æłĩæĺ¯
    -0.06
    ãģ©ãĤĤ
    -0.06
    -death
    -0.06
    POSITIVE LOGITS
    å¿ħè¦ģæŶ
    0.07
    ½
    0.07
    idar
    0.07
    usus
    0.07
    aro
    0.07
    idos
    0.07
    åĽ½å®ī
    0.07
    ãĥ«ãĥĪ
    0.07
    é¢Ĥ
    0.07
    áĢº
    0.06
    Activations Density 0.000%

    No Known Activations