© 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. 40645
    Prev
    Next
    INDEX
    Explanations

    file name extensions `.txt`, `Excel`

    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
    .keys
    -0.08
     Bota
    -0.07
    ä¹ŁæĽ´
    -0.07
    रà¥įस
    -0.07
    ä¸Ģå¾ĭ
    -0.07
    YNAM
    -0.07
    era
    -0.06
     Gara
    -0.06
    odesk
    -0.06
    mara
    -0.06
    POSITIVE LOGITS
    hus
    0.08
    ubre
    0.08
    à¦ľà§ĩ
    0.07
    -side
    0.07
    maz
    0.07
     antagon
    0.07
     concurrently
    0.06
     sides
    0.06
    åIJĪ并
    0.06
     moist
    0.06
    Activations Density 0.117%

    No Known Activations