© 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. 12761
    Prev
    Next
    INDEX
    Explanations

    titration

    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
    heits
    -0.10
     изÑĢа
    -0.08
    elige
    -0.08
    äºĨæĮĩ
    -0.08
    iliary
    -0.08
    oreal
    -0.08
    tics
    -0.07
     Ðijожи
    -0.07
     Caucus
    -0.07
    :block
    -0.07
    POSITIVE LOGITS
     ulang
    0.09
    uento
    0.07
    GBT
    0.07
    å¾Ģ
    0.07
    ian
    0.07
    å¼Ģå§ĭåIJİ
    0.07
    ster
    0.07
    agg
    0.06
     conducted
    0.06
    ä¸ĬæĿ¥çļĦ
    0.06
    Activations Density 0.007%

    No Known Activations