© 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. 61442
    Prev
    Next
    INDEX
    Explanations

    None or false boolean values

    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
    ropp
    -0.07
    eners
    -0.07
    arb
    -0.07
    olia
    -0.07
    庶
    -0.06
    UED
    -0.06
    aju
    -0.06
    anner
    -0.06
    erat
    -0.06
    λιά
    -0.06
    POSITIVE LOGITS
    è¿Ļ个社ä¼ļ
    0.07
     bowiem
    0.07
    _REQUIRE
    0.07
    çĥ«
    0.07
    ksam
    0.07
    æĥ¦è®°
    0.07
    acruz
    0.07
    å¿ĹåĪļ
    0.07
    kens
    0.07
    ×ķ×Ŀ
    0.07
    Activations Density 0.010%

    No Known Activations