© 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. 58173
    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
    indsight
    -0.08
    upan
    -0.08
    гни
    -0.08
    ettino
    -0.08
    ELLOW
    -0.07
    ioni
    -0.07
    Ŀ¼
    -0.07
    ellini
    -0.07
    ellow
    -0.07
    ptest
    -0.07
    POSITIVE LOGITS
     often
    0.07
    åħ¼
    0.06
    åĬłæĭ¿å¤§
    0.06
    /operators
    0.06
    絡
    0.06
     aur
    0.06
    zur
    0.06
    to
    0.06
    å¾Ĺ人
    0.06
     realized
    0.06
    Activations Density 0.000%

    No Known Activations