© 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. 65352
    Prev
    Next
    INDEX
    Explanations

    these or those

    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
     chÄĥng
    -0.08
    âĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢâĶĢ
    -0.07
     stuff
    -0.07
    ror
    -0.07
     everyone
    -0.07
    å¾Ĺåĥı
    -0.07
    ä¸Ģ家
    -0.06
    åĪĨæ°´
    -0.06
    ä¸ĢåĪĩ
    -0.06
    æīĢæľī人çļĦ
    -0.06
    POSITIVE LOGITS
    gadas
    0.09
    enses
    0.08
    cape
    0.08
    fél
    0.08
    mert
    0.08
     listed
    0.08
    ses
    0.08
    gada
    0.07
    gados
    0.07
     dozen
    0.07
    Activations Density 0.276%

    No Known Activations