© 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. 51620
    Prev
    Next
    INDEX
    Explanations

    support and community events

    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
    voud
    -0.09
    å±¹
    -0.08
    ÑĤаки
    -0.08
    bidden
    -0.08
    /as
    -0.07
    ativer
    -0.07
    /if
    -0.07
    æĪĸå¤ļ个
    -0.07
    zych
    -0.07
    atuur
    -0.07
    POSITIVE LOGITS
    ing
    0.11
    们éĥ½
    0.09
    ä¸įäºĨ
    0.09
    äºĨ两
    0.08
    ize
    0.08
    ed
    0.08
    äºĨä¸Ģ个
    0.08
     the
    0.08
     them
    0.08
    äºĨä¸ŃåĽ½
    0.08
    Activations Density 0.745%

    No Known Activations