© 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
    2. Qwen3.5-9B Base
    3. 15-QWENSCOPE-RES-64K
    4. 24666
    Prev
    Next
    INDEX
    Explanations

    asking for advice or help

    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
     Kunde
    -0.07
    é¾Ħ
    -0.07
    æ·ĭæ¼ĵå°½èĩ´
    -0.07
    cia
    -0.07
    ernos
    -0.06
    åij½
    -0.06
    á»ĩn
    -0.06
    ãģĵãĤĵ
    -0.06
    ãģŀ
    -0.06
    踪
    -0.06
    POSITIVE LOGITS
    ellis
    0.08
    ç»ĵæŀĦåĴĮ
    0.08
    å¸ĥå±ĢåĴĮ
    0.08
    äºĭåħ³
    0.08
    ç»ĵæŀĦä¸İ
    0.07
    ä¸įæŃ»
    0.07
    à¹Ģà¸Ľà¹ĩà¸Ļสิà¹Īà¸ĩ
    0.07
    çļĦå¿ĥæĢĿ
    0.07
    åį¡åĴĮ
    0.07
    ialis
    0.07
    Activations Density 0.005%

    No Known Activations