© 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. 58127
    Prev
    Next
    INDEX
    Explanations

    name, title, or type

    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
    ÙĬØ©
    -0.10
    ation
    -0.10
    ing
    -0.09
    ा
    -0.09
    a
    -0.09
    ا
    -0.08
    à¯į
    -0.08
    aikan
    -0.08
    ular
    -0.08
    ive
    -0.08
    POSITIVE LOGITS
    çĦ¶æĺ¯
    0.13
    ————————————————
    0.11
    ãĥ£
    0.11
    kannya
    0.09
    hone
    0.09
    人
    0.09
    人èĥ½
    0.08
    ir
    0.08
    zelfde
    0.08
    вок
    0.08
    Activations Density 0.046%

    No Known Activations