© 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. 33424
    Prev
    Next
    INDEX
    Explanations

    poor quality or performance

    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
    ä¸įçĶ¨åĨį
    -0.08
    溢
    -0.07
     gracias
    -0.07
    upil
    -0.07
     nyug
    -0.07
    ä¸įåı¯èĥ½çļĦ
    -0.07
     grâce
    -0.07
     dziÄĻki
    -0.07
    ä¸įçĶ¨æĭħå¿ĥ
    -0.07
    åıªåı¯æĥľ
    -0.07
    POSITIVE LOGITS
     Worse
    0.15
     :(
    0.13
     worse
    0.13
    è¿ĺä¸įå¦Ĥ
    0.12
    åı¯æĢľçļĦ
    0.12
     poorer
    0.11
     poor
    0.11
     disappointing
    0.10
     dismal
    0.10
     poorest
    0.10
    Activations Density 0.270%

    No Known Activations