© 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. 1881
    Prev
    Next
    INDEX
    Explanations

    boho, beatnik, indie, alternative

    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
    æ°´åĻ¨
    -0.07
    åĬŁå¾·
    -0.07
    å¾ģå¾Ĺ
    -0.07
    ÑģкÑĥÑģ
    -0.07
    agrid
    -0.07
    æĪĺå½¹
    -0.07
    åħĥ代
    -0.06
    gebung
    -0.06
    à¸Ĺà¸Ńà¸Ķ
    -0.06
     statically
    -0.06
    POSITIVE LOGITS
    é£İæł¼çļĦ
    0.10
    -style
    0.10
    人士
    0.10
    人士çļĦ
    0.09
    é¢¨æł¼
    0.09
     style
    0.09
    é£İæł¼
    0.09
    -leaning
    0.09
    style
    0.08
    -inspired
    0.08
    Activations Density 0.358%

    No Known Activations