© 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. 16234
    Prev
    Next
    INDEX
    Explanations

    functions and class definitions

    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
    èį
    -0.07
    oral
    -0.07
    ivat
    -0.07
     Freitas
    -0.06
    ï
    -0.06
    \_
    -0.06
    iene
    -0.06
    .mozilla
    -0.06
    à¹ģà¸ķà¹Īà¸ĩ
    -0.06
    åħŃæĪIJ
    -0.06
    POSITIVE LOGITS
    ä¸İ被
    0.09
    çĭŀ
    0.08
    zze
    0.08
     licha
    0.08
    zelf
    0.07
    ä¸ĭæľŁ
    0.07
    ļĮ
    0.07
    zeg
    0.07
    ntl
    0.07
    代çIJĨæľįåĬ¡
    0.07
    Activations Density 0.093%

    No Known Activations