© 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. 40491
    Prev
    Next
    INDEX
    Explanations

    i 'm / i 've / i'll

    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
    ORLD
    -0.08
    orld
    -0.08
    ekl
    -0.07
    onium
    -0.07
    æĪijç»Ļä½ł
    -0.07
    वल
    -0.07
    ëĩ¨
    -0.07
    ighth
    -0.07
    åı«ä½ł
    -0.07
    åª
    -0.06
    POSITIVE LOGITS
    zig
    0.08
    've
    0.08
    'll
    0.08
    .e
    0.08
    lass
    0.07
    ’ll
    0.07
     ëĺIJíķľ
    0.07
    ä¹ĭæīĢ以
    0.07
    nota
    0.07
    ’ve
    0.07
    Activations Density 0.367%

    No Known Activations