© 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. 7424
    Prev
    Next
    INDEX
    Explanations

    start of time/range

    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
    ewise
    -0.07
    ellar
    -0.07
    ä¸įå¤ļçļĦ
    -0.07
    elper
    -0.07
    zcze
    -0.07
    è§ģ解
    -0.07
    zyd
    -0.06
    illes
    -0.06
    ä¸ļåĬ¡æ°´å¹³
    -0.06
    velope
    -0.06
    POSITIVE LOGITS
    /start
    0.08
    èµ·å§ĭ
    0.08
     bound
    0.08
    destruct
    0.08
     наÑĩалом
    0.07
    start
    0.07
    æĭ¬
    0.07
    owitz
    0.07
    .getStart
    0.07
    erval
    0.07
    Activations Density 0.036%

    No Known Activations