© 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. 64252
    Prev
    Next
    INDEX
    Explanations

    asking about specific intents

    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
    zi
    -0.07
    ierra
    -0.07
    åŁł
    -0.07
    ijs
    -0.06
    hei
    -0.06
    è¶ħ强
    -0.06
    gena
    -0.06
    iator
    -0.06
    estra
    -0.06
    cÃŃ
    -0.06
    POSITIVE LOGITS
     именно
    0.08
    çļĦä¸įæĺ¯
    0.08
     Ñģаме
    0.08
    ãģĤãģı
    0.08
    æķĪæŀľåĴĮ
    0.07
    °
    0.07
    è¤
    0.07
    æ·
    0.07
    ä¸įæĺ¯ä½ł
    0.07
    èĢĮä¸Ķè¦ģ
    0.07
    Activations Density 0.004%

    No Known Activations