© 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. 39952
    Prev
    Next
    INDEX
    Explanations

    health, intervention, growth, quality, lighting, connections

    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
    èĩ³å°ij
    -0.06
    ä¸ĭ
    -0.06
    agle
    -0.06
    æĿŁ
    -0.06
     either
    -0.06
    èĮµ
    -0.05
    åĩĨ
    -0.05
    è¦ģä¹Ī
    -0.05
    天ä¸ĭ
    -0.05
    cheme
    -0.05
    POSITIVE LOGITS
    åĬłè½½æĽ´å¤ļ
    0.09
    uña
    0.09
    EXTERNAL
    0.08
    å¼Ģæľį
    0.08
    euw
    0.08
    èĩªå·±çļĦ梦æĥ³
    0.08
    ÃŃdu
    0.08
    validators
    0.08
    زÙĨ
    0.08
    ICODE
    0.08
    Activations Density 0.001%

    No Known Activations