© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 46750
    Prev
    Next
    INDEX
    Explanations

    diagrams and models

    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
    ½
    -0.07
    çŁ³æ£ī
    -0.07
    raq
    -0.07
    ENA
    -0.07
    umping
    -0.07
    _argument
    -0.07
     ogl
    -0.07
    Increment
    -0.06
    oppers
    -0.06
    plier
    -0.06
    POSITIVE LOGITS
     diagram
    0.17
     Diagram
    0.14
     schematic
    0.13
    æµģç¨ĭåĽ¾
    0.13
     schem
    0.12
    Diagram
    0.12
    示æĦıåĽ¾
    0.12
    chematic
    0.12
     diagrams
    0.12
    åĽ¾ç¤º
    0.12
    Activations Density 0.119%

    No Known Activations