© 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. 15187
    Prev
    Next
    INDEX
    Explanations

    `*` or `:` followed by labels

    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
    ]][
    -0.07
    )][
    -0.06
    urz
    -0.06
    æĹ¢çĦ¶
    -0.06
    .IsAny
    -0.06
     Personn
    -0.06
    áĥĶáĥĽ
    -0.06
    ulti
    -0.06
    buster
    -0.06
    '](
    -0.05
    POSITIVE LOGITS
    æĶ¶èĹıæľ¬ç«Ļ
    0.08
    JAKARTA
    0.08
    çıŃåĪĹ
    0.08
     medio
    0.07
    翼翼
    0.07
    åĭĴæĸ¯
    0.07
    reur
    0.07
    bsite
    0.07
     Pozn
    0.07
    appa
    0.07
    Activations Density 0.017%

    No Known Activations