© 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. 37940
    Prev
    Next
    INDEX
    Explanations

    superoxide dismutase

    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
    oskop
    -0.07
    æĭīåħĭ
    -0.07
    ijo
    -0.06
    ạm
    -0.06
    åŃĺ
    -0.06
    iju
    -0.06
    rip
    -0.06
    ÎŁÎ£
    -0.06
    okra
    -0.06
     Braves
    -0.06
    POSITIVE LOGITS
    umul
    0.08
    注åĨĮä¼ļåijĺ
    0.08
    acob
    0.08
    croll
    0.08
    书åIJ§
    0.07
    leep
    0.07
    Ñĩник
    0.07
     Canter
    0.07
    è¿Ľé©»
    0.07
    天éŨ
    0.07
    Activations Density 0.004%

    No Known Activations