© 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. 32709
    Prev
    Next
    INDEX
    Explanations

    sugar inroll overbright ,execution ofinclude entryeasy entrycopied /back

    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
     pleasantly
    -0.09
     respectfully
    -0.08
     appropriately
    -0.08
    缮çŀª
    -0.08
    umi
    -0.08
     hopefully
    -0.08
    Periph
    -0.07
    UMA
    -0.07
    æ´½
    -0.07
     properly
    -0.07
    POSITIVE LOGITS
     unchecked
    0.10
     Worse
    0.09
    ä¸ĩä¸Ģ
    0.08
    ãģ£ãģ¦ãģĹãģ¾ãģĨ
    0.08
     indiscrim
    0.08
    åį³ä½¿æĺ¯
    0.08
    å¾Ī容æĺĵ被
    0.08
    even
    0.08
     even
    0.08
     worse
    0.08
    Activations Density 0.158%

    No Known Activations