© 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. 40413
    Prev
    Next
    INDEX
    Explanations

    ratio or product

    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
    åħ¶äºº
    -0.08
    ska
    -0.07
     gerek
    -0.07
    éĤ£ä½ł
    -0.06
    ä»İ天
    -0.06
    edig
    -0.06
    森
    -0.06
    oty
    -0.06
    alda
    -0.06
    s
    -0.06
    POSITIVE LOGITS
    aison
    0.08
     between
    0.08
     thereof
    0.08
    leve
    0.08
    utex
    0.08
    ennon
    0.08
    etween
    0.07
    ربÙĪÙĦ
    0.07
    ukum
    0.07
    两边çļĦ
    0.07
    Activations Density 0.008%

    No Known Activations