© 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. 10253
    Prev
    Next
    INDEX
    Explanations

    still and without

    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
    insta
    -0.08
    agia
    -0.07
    urun
    -0.07
    inspection
    -0.07
    ney
    -0.07
    åIJĮå¿Ĺ为
    -0.07
    undra
    -0.07
    vely
    -0.07
    åĭĭ
    -0.07
    æł
    -0.07
    POSITIVE LOGITS
    çħ§æł·
    0.09
    ä¸įä¼ļå½±åĵį
    0.09
     acceptable
    0.08
    åıªè¦ģåľ¨
    0.08
    ä¾ĿçĦ¶
    0.08
    大ä¸įäºĨ
    0.08
    ä¸įå½±åĵį
    0.07
    ä¾Ŀæŧæĺ¯
    0.07
    .IsValid
    0.07
     maintaining
    0.07
    Activations Density 0.160%

    No Known Activations