© 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. 62813
    Prev
    Next
    INDEX
    Explanations

    Proper noun beginnings

    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
    aeper
    -0.07
    uffs
    -0.07
    yect
    -0.07
    对æľī
    -0.07
     altrett
    -0.07
    losion
    -0.07
    ãĥ¼ãĤ¿ãĥ¼
    -0.06
    oncini
    -0.06
    aurus
    -0.06
    ãĥ¼ãĥĦ
    -0.06
    POSITIVE LOGITS
    å±±æĻ¯åĮº
    0.07
    éĥ¨éŨèģĶåIJĪ
    0.07
     *âĢŀ
    0.06
    å¹´çļĦåıijå±ķ
    0.06
    人åijĺè¿Ľè¡Į
    0.06
    pum
    0.06
    à¸ģร
    0.06
     terbak
    0.06
    代夫
    0.06
    ativamente
    0.06
    Activations Density 2.372%

    No Known Activations