© 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. 48744
    Prev
    Next
    INDEX
    Explanations

    address::unserialize(Ui::gui_coll_helper

    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
    .getInstance
    -0.07
    son
    -0.06
    ricks
    -0.06
    ycz
    -0.06
    èĢģå¸Ī说
    -0.06
    åİĨæŶ
    -0.06
    eli
    -0.06
    ivan
    -0.06
    AVA
    -0.06
    çİĩåħĪ
    -0.06
    POSITIVE LOGITS
    ķ
    0.08
    авли
    0.08
    à¥ģर
    0.07
    ãģªãĤĤãģ®
    0.07
    opaque
    0.07
    unis
    0.07
    ones
    0.07
    trup
    0.07
    one
    0.07
    ulet
    0.07
    Activations Density 0.074%

    No Known Activations