© 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. 57735
    Prev
    Next
    INDEX
    Explanations

    prevent, discourage, slow, deliberately

    np_acts-logits-general · gemini-2.5-flash-lite
    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
    imana
    -0.07
    éro
    -0.07
    æĭ¯
    -0.07
    udy
    -0.07
     Reign
    -0.07
    载人
    -0.07
    issi
    -0.07
    dirs
    -0.07
    æĭŃ
    -0.07
    åı¤éģĵ
    -0.06
    POSITIVE LOGITS
    éĺ²æŃ¢
    0.12
    æķħæĦı
    0.12
     discourage
    0.12
    éĺ»æŃ¢
    0.12
    以éĺ²æŃ¢
    0.11
     discour
    0.11
     deliberately
    0.11
    为äºĨéĺ²æŃ¢
    0.11
    为éĺ²æŃ¢
    0.11
     purposely
    0.11
    Activations Density 0.243%

    No Known Activations