© 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. 26039
    Prev
    Next
    INDEX
    Explanations

    copy constructor

    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
    éļĪ
    -0.11
    sburg
    -0.10
    sker
    -0.10
    cliffe
    -0.10
    pä
    -0.09
    eenth
    -0.09
    agni
    -0.09
    acruz
    -0.09
    psilon
    -0.09
    ê°ľíĺģ
    -0.08
    POSITIVE LOGITS
    .deepcopy
    0.11
    aneous
    0.09
    able
    0.08
    /cop
    0.08
    ing
    0.08
    ulative
    0.08
     copies
    0.07
    truncate
    0.07
    ़
    0.07
    æĪĸåĪłéĻ¤
    0.07
    Activations Density 0.076%

    No Known Activations