© 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. 48844
    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
    æ°¸åħ´
    -0.07
    añ
    -0.06
    astre
    -0.06
    hen
    -0.06
    hr
    -0.06
    äºĨæĮĩ
    -0.06
    æĺ¯æĮĩåľ¨
    -0.06
    har
    -0.06
    次
    -0.06
     hr
    -0.06
    POSITIVE LOGITS
    amd
    0.08
    itori
    0.07
     NotImplementedError
    0.07
     autogenerated
    0.07
    	Copyright
    0.07
     desac
    0.07
    UiThread
    0.07
    utorial
    0.07
    emachine
    0.07
    \/\/
    0.07
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.