© 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. 62492
    Prev
    Next
    INDEX
    Explanations

    numbers and dates

    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
    igent
    -0.08
    ijan
    -0.08
    对å®ĥ
    -0.08
    jeno
    -0.07
    ä¸ĢæĦı
    -0.07
    igente
    -0.07
    åĨįåĬłåħ¥
    -0.07
    å¸¸åľ¨
    -0.07
    trag
    -0.07
    å¥Ķæ³¢
    -0.07
    POSITIVE LOGITS
    rza
    0.07
    Nam
    0.07
    å¯Ħ
    0.06
     наÑģÑĤ
    0.06
    æį»
    0.06
    esak
    0.06
    à§įত
    0.06
    è·ĮèIJ½
    0.06
    ç¥Ģ
    0.06
    讼
    0.06
    Activations Density 0.016%

    No Known Activations