© 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. 50861
    Prev
    Next
    INDEX
    Explanations

    correct statements

    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
    åIJĦè¡ĮåIJĦ
    -0.07
    .sourceforge
    -0.07
    asso
    -0.07
    anford
    -0.06
    代表çļĦ
    -0.06
    ownt
    -0.06
    çĥĤ
    -0.06
    sov
    -0.06
    ç¿°
    -0.06
    ç«ĻåĨħæIJľç´¢
    -0.06
    POSITIVE LOGITS
    æŃ£ç¡®çļĦæĺ¯
    0.11
     statements
    0.10
     correct
    0.10
    Statements
    0.10
    æŃ£ç¡®çļĦ
    0.10
     incorrect
    0.10
     describing
    0.10
    æııè¿°äºĨ
    0.09
    éĻĪè¿°
    0.09
     correctly
    0.09
    Activations Density 0.007%

    No Known Activations