© 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. 40793
    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
    èĢĮä¸Ĭ
    -0.07
    omb
    -0.07
    å¸ĮæľĽåľ¨
    -0.07
    holz
    -0.07
    ä¸įæŃ¢
    -0.07
    lieder
    -0.06
    äºĭ件ä¸Ń
    -0.06
    èĢĮåħ¥
    -0.06
    Ïĩε
    -0.06
    èĢĮæĹł
    -0.06
    POSITIVE LOGITS
    们éĥ½
    0.10
    esco
    0.07
    jit
    0.07
    们çļĦ
    0.07
    urn
    0.07
    asures
    0.07
     ↵        ↵
    0.07
    ipper
    0.07
     handleError
    0.07
    unft
    0.06
    Activations Density 0.000%

    No Known Activations