© 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. 49773
    Prev
    Next
    INDEX
    Explanations

    check if condition

    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
    ç¾İéħĴ
    -0.07
    on
    -0.07
    åĪļæĢ§
    -0.07
     [&](
    -0.07
    ÑĤÑĥÑĢ
    -0.06
    åıįå¤į
    -0.06
    çļĦå¿ĥèĦı
    -0.06
    orte
    -0.06
    struction
    -0.06
    ạc
    -0.06
    POSITIVE LOGITS
    ReturnValue
    0.08
    çĺª
    0.08
    åºĬ
    0.07
    ä¸įå¾Ĺ以任ä½ķ
    0.07
    èIJ½ä¸ĭ
    0.07
    Mock
    0.07
     sublist
    0.07
    isal
    0.07
    ussin
    0.07
    atera
    0.07
    Activations Density 0.028%

    No Known Activations