© 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. 42062
    Prev
    Next
    INDEX
    Explanations

    dollars and services

    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
    CLR
    -0.07
    ÙijÙĨ
    -0.07
    Grammar
    -0.07
    æĨ¬
    -0.07
    çĽ¸æľĽ
    -0.06
    ä»Ĩ
    -0.06
    rew
    -0.06
    .Reporting
    -0.06
    éļ¶
    -0.06
    èĩªå·±çļĦçĶŁåij½
    -0.06
    POSITIVE LOGITS
    翼翼
    0.08
    bove
    0.08
    insky
    0.07
    以ä¸Ĭ
    0.07
    inent
    0.07
    ç¾ļ
    0.07
    elius
    0.07
    æ±Ĥç²¾
    0.07
    ìĩĦ
    0.07
    <source
    0.07
    Activations Density 0.009%

    No Known Activations