© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 17769
    Prev
    Next
    INDEX
    Explanations

    numbers and units respectively

    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
    imir
    -0.07
    awa
    -0.06
    join
    -0.06
    çĴ§
    -0.06
    udd
    -0.06
    omet
    -0.06
    ä¸īæĸ¹
    -0.06
    ava
    -0.06
    oom
    -0.06
    idd
    -0.05
    POSITIVE LOGITS
    åĪĨåĪ«
    0.09
    andest
    0.09
     respectively
    0.09
    ianya
    0.08
     ÑģооÑĤвеÑĤÑģÑĤвенно
    0.08
    åĪĨåĪ¥
    0.08
    åĪĨåĪ«åľ¨
    0.08
     respectiv
    0.08
    åĪĨåĪ«ä¸º
    0.08
    piring
    0.08
    Activations Density 0.019%

    No Known Activations