© 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. 42676
    Prev
    Next
    INDEX
    Explanations

    duty and obligations

    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
    abouts
    -0.09
    ething
    -0.08
     Ovviamente
    -0.08
    plet
    -0.08
    arer
    -0.08
     بÛĮÙĨÛĮ
    -0.07
    agno
    -0.07
    åĬ¿å¤´
    -0.07
    icola
    -0.07
     Purtroppo
    -0.07
    POSITIVE LOGITS
    ments
    0.08
    åĴĮä¹īåĬ¡
    0.08
    åĴĮ责任
    0.07
    ç¹ģéĩį
    0.07
    年满
    0.07
    fully
    0.07
    /dis
    0.07
    escu
    0.07
    iful
    0.07
    /res
    0.07
    Activations Density 0.033%

    No Known Activations