© 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. 62933
    Prev
    Next
    INDEX
    Explanations

    choice "(c)"

    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
    ä¸Ń大
    -0.07
    åºĬ
    -0.07
    侨
    -0.07
    ÏĥÏĦε
    -0.07
    ÑĤоÑĢи
    -0.06
    ertes
    -0.06
    enea
    -0.06
     intending
    -0.06
    å»Ĭ
    -0.06
    anea
    -0.06
    POSITIVE LOGITS
    estal
    0.07
    UNUSED
    0.07
    pal
    0.07
    jit
    0.07
    ukkan
    0.07
    uson
    0.07
    à¥Ĥस
    0.07
    ÑĢÑĥÑģ
    0.07
    èķĥ
    0.07
     kẻ
    0.06
    Activations Density 0.003%

    No Known Activations