© 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. 2554
    Prev
    Next
    INDEX
    Explanations

    statement of need or purpose

    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
    quals
    -0.09
    /qu
    -0.08
    管çĶ¨
    -0.08
    没çĶ¨
    -0.08
    pike
    -0.08
    ales
    -0.08
    以åħ¶
    -0.07
    aliser
    -0.07
    ãĤ±ãĥ³
    -0.07
    ÐijÐł
    -0.07
    POSITIVE LOGITS
    èIJ¨æĸ¯
    0.07
    ily
    0.07
    jin
    0.06
    ëĿ¼ë©´
    0.06
    æݨ移
    0.06
    igo
    0.06
    enen
    0.06
    ually
    0.06
    igin
    0.05
    جاÙĦ
    0.05
    Activations Density 0.008%

    No Known Activations