© 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. 29684
    Prev
    Next
    INDEX
    Explanations

    Chinese names and technical terms

    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
    adero
    -0.08
    ulun
    -0.08
    enido
    -0.07
    çĽĬ
    -0.07
    gena
    -0.07
    ccion
    -0.07
    ½Ķ
    -0.07
    nia
    -0.07
    swith
    -0.07
    noinspection
    -0.07
    POSITIVE LOGITS
    ä¹ĭ为
    0.07
    tua
    0.06
    ç®Ģ称
    0.06
    вÑĮÑİ
    0.06
    簡稱
    0.06
    reif
    0.06
    éĶ¦æłĩèµĽ
    0.06
    åİŁå®¡è¢«åijĬ
    0.06
    çĭ¸
    0.06
     knock
    0.06
    Activations Density 0.048%

    No Known Activations