© 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. 29958
    Prev
    Next
    INDEX
    Explanations

    `the` followed by nouns or after determiners

    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
     prê
    -0.06
    åıĪä¸Ģ
    -0.06
    cede
    -0.06
    èĵĿçŃ¹
    -0.06
    gris
    -0.06
    强度é«ĺ
    -0.06
    imbau
    -0.06
    éĿĴåħī
    -0.06
     UIControl
    -0.06
    转载请éĻĦä¸Ĭ
    -0.06
    POSITIVE LOGITS
    ubo
    0.07
    ä»ĭ
    0.07
    _OM
    0.07
    вÑĸв
    0.07
    langs
    0.07
    åĬªåĬĽåģļåĪ°
    0.07
    jac
    0.07
    à¸Ľà¸²à¸ģ
    0.07
    så
    0.07
    çĤ¹åĩ»ä¸ĭæĸ¹
    0.07
    Activations Density 0.056%

    No Known Activations