© 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. 45833
    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
     Gow
    -0.07
    ubil
    -0.07
    å±±éķĩ
    -0.06
    ä¸įä¸ĭæĿ¥
    -0.06
    {_
    -0.06
    {@
    -0.06
    åİ®
    -0.06
    ç§ĴéĴŁ
    -0.06
    &_
    -0.06
    ÑģÑĤе
    -0.06
    POSITIVE LOGITS
    äº
    0.08
    dd
    0.07
    åĨ²åĪº
    0.06
    æĬĢæľ¯åıĬ
    0.06
    dden
    0.06
    porn
    0.06
    çĶ°
    0.06
    zyst
    0.06
    .velocity
    0.06
    ocha
    0.06
    Activations Density 0.000%

    No Known Activations