© 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. 11954
    Prev
    Next
    INDEX
    Explanations

    chemical suffixes and compounds

    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
    å¾·æīį
    -0.07
    bard
    -0.07
    端起
    -0.07
    amah
    -0.07
     zen
    -0.07
    acons
    -0.07
    æIJŃéħįçļĦ
    -0.07
    缸åºĶ
    -0.07
    nh
    -0.07
    Initializer
    -0.06
    POSITIVE LOGITS
    elok
    0.09
    éģĵéģĵ
    0.08
    æĹ¨åľ¨
    0.07
    endorf
    0.07
    çļĦæĿ¡ä»¶ä¸ĭ
    0.06
    æĿ¡ä»¶ä¸ĭ
    0.06
    æ²Ľ
    0.06
    ansom
    0.06
    uera
    0.06
    ueille
    0.06
    Activations Density 0.010%

    No Known Activations