© 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. 32790
    Prev
    Next
    INDEX
    Explanations

    Please forgive

    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¸į妨
    -0.07
    çķĶ
    -0.07
    以åıĬ对
    -0.07
    æĥĨ
    -0.07
    igno
    -0.07
     ìĹ°
    -0.07
    ấn
    -0.07
    idere
    -0.07
    anco
    -0.07
    <Double
    -0.07
    POSITIVE LOGITS
    ç»Ŀ对ä¸įæĺ¯
    0.09
     diversity
    0.08
    ç»Ŀä¸įæĺ¯
    0.08
     FALSE
    0.08
    FALSE
    0.08
    çīĩéĿ¢
    0.08
    ä¸ĸçķĮä¸Ĭ
    0.08
     Diversity
    0.08
     False
    0.08
    åıį驳
    0.08
    Activations Density 0.014%

    No Known Activations