© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 2407
    Prev
    Next
    INDEX
    Explanations

    boolean value or flag

    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
    etim
    -0.07
     exac
    -0.07
    xes
    -0.07
    çļĦèĥĮå½±
    -0.07
    FIELDS
    -0.07
    绵绵
    -0.07
    ornings
    -0.07
    ourn
    -0.07
    поли
    -0.07
    omanip
    -0.07
    POSITIVE LOGITS
    åĪ¤æĸŃ
    0.19
    åĪ¤å®ļ
    0.17
    åĨ³å®ļæĺ¯åIJ¦
    0.17
    æĿ¥åĪ¤æĸŃ
    0.16
    çļĦåĪ¤æĸŃ
    0.15
    åĪ¤æĸ·
    0.15
    åĪ¤
    0.15
     whether
    0.15
     boolean
    0.14
     Boolean
    0.14
    Activations Density 0.565%

    No Known Activations