© 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. 62104
    Prev
    Next
    INDEX
    Explanations

    False

    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
    ())[
    -0.08
    ))[
    -0.08
    UMENT
    -0.07
    ä»»æĢ¨
    -0.07
    >:</
    -0.07
    èģĮä¸ļæĬĢæľ¯åѦéĻ¢
    -0.07
    ä¸į足çļĦ
    -0.07
    æķĪçİĩé«ĺ
    -0.07
    Opaque
    -0.07
    STRUCTOR
    -0.07
    POSITIVE LOGITS
    æķħæѤ
    0.08
    indic
    0.08
    说æĺİ
    0.08
    æŃ¤é¡¹
    0.08
    веÑĤа
    0.07
    æķħ
    0.07
    åĽłæѤ
    0.07
     Therefore
    0.06
     СледоваÑĤелÑĮно
    0.06
    è¿Ļ说æĺİ
    0.06
    Activations Density 0.008%

    No Known Activations