© 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. 1854
    Prev
    Next
    INDEX
    Explanations

    advocate for

    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
    ish
    -0.06
    alc
    -0.06
    ishes
    -0.06
    è¶ĬæĿ¥è¶Ĭå¤ļ
    -0.06
    ×
    -0.06
    å°±æĺ¯è¿Ļæł·
    -0.06
    j
    -0.06
    èĤ¡ä»½çļĦ
    -0.06
    رÙģت
    -0.06
    åĴĮç¾İåĽ½
    -0.06
    POSITIVE LOGITS
    ä¸įçĿĢ
    0.09
    оÑĤа
    0.08
    otime
    0.08
    èĢħ为
    0.08
    å¹´åį¡
    0.08
    bauer
    0.08
    mdb
    0.07
    otu
    0.07
    еÑģе
    0.07
    anisme
    0.07
    Activations Density 0.002%

    No Known Activations