© 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. 8699
    Prev
    Next
    INDEX
    Explanations

    digits and numbers

    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
    æŃ£åĽł
    -0.07
    jected
    -0.07
    amp
    -0.07
    PEAR
    -0.07
    pany
    -0.07
    æīĵ好
    -0.06
    anch
    -0.06
    -0.06
    gor
    -0.06
    ney
    -0.06
    POSITIVE LOGITS
    eenth
    0.11
    ABCDEFG
    0.10
    第åħ«æĿ¡
    0.10
    åħ«ä¸ª
    0.09
    eight
    0.08
    ä¸ĥåįģäºĮ
    0.08
     eighth
    0.08
    -eight
    0.07
    åħ«å¤§
    0.07
    ائ
    0.07
    Activations Density 0.307%

    No Known Activations