© 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. 25634
    Prev
    Next
    INDEX
    Explanations

    numerical calculations

    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
    raig
    -0.07
    ä¸īä¸Ń
    -0.07
    imm
    -0.07
    aside
    -0.07
    ree
    -0.07
    vars
    -0.07
    oule
    -0.07
    amel
    -0.06
     sting
    -0.06
    emes
    -0.06
    POSITIVE LOGITS
    ksam
    0.07
    velt
    0.07
    iern
    0.07
    arty
    0.07
    çļĦæĿ±è¥¿
    0.07
    iendo
    0.06
    游åŃIJ
    0.06
    rias
    0.06
    FOUNDATION
    0.06
    гни
    0.06
    Activations Density 0.002%

    No Known Activations