© 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. 19307
    Prev
    Next
    INDEX
    Explanations

    resetting to zero

    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
    åĨħ容æľī
    -0.07
    è¿ĽéĢĢ
    -0.07
    人头
    -0.07
    _EXPORT
    -0.07
    unload
    -0.07
    帼
    -0.07
     clic
    -0.07
    à¥įव
    -0.07
    èİħ
    -0.07
    .construct
    -0.07
    POSITIVE LOGITS
    éĩįæĸ°å¼Ģå§ĭ
    0.13
    éĩįæĸ°
    0.11
     resumed
    0.09
    åıĪå¼Ģå§ĭ
    0.08
    Ãły
    0.08
     reset
    0.08
    éĩįåĽŀ
    0.07
    ingle
    0.07
    /reset
    0.07
     Reset
    0.07
    Activations Density 0.009%

    No Known Activations