© 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. 12279
    Prev
    Next
    INDEX
    Explanations

    numbered, seeded, coordinates, binary, index

    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
    éľ²
    -0.08
    serie
    -0.07
    å¿ĥåŃĺ
    -0.07
    åķĨä¼ļ
    -0.07
     Enth
    -0.07
    queira
    -0.07
    urier
    -0.07
    rove
    -0.07
     terror
    -0.07
    ç¼Ī
    -0.07
    POSITIVE LOGITS
    MED
    0.07
    åIJĦéķĩ
    0.07
    èİĺ
    0.07
    åIJĦæĿij
    0.06
    ç²
    0.06
    inet
    0.06
    Maintenance
    0.06
    缴è§Ĵ
    0.06
    æļĹæļĹ
    0.06
    åIJĦ乡éķĩ
    0.06
    Activations Density 0.023%

    No Known Activations