© 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. 42796
    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
    elder
    -0.08
    evin
    -0.08
    /Common
    -0.08
    å¥ĭæĸĹ缮æłĩ
    -0.08
    RITE
    -0.07
    iels
    -0.07
    对éĤ£äºĽ
    -0.07
    åħįåĨł
    -0.07
    ushman
    -0.07
    bart
    -0.07
    POSITIVE LOGITS
    __/
    0.07
    èĤ¥
    0.06
     zufolge
    0.06
    ybrid
    0.06
    ientos
    0.06
    ivity
    0.06
    忽
    0.06
    “
    0.06
    opus
    0.06
    ات
    0.06
    Activations Density 0.000%

    No Known Activations