© 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. 62092
    Prev
    Next
    INDEX
    Explanations

    this (followed by noun)

    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
    æĢ§è¡Į为
    -0.08
    åĮĸçļĦ
    -0.07
    éné
    -0.07
    otta
    -0.07
    lect
    -0.07
    è·Įåģľ
    -0.07
    ặn
    -0.07
    zá
    -0.07
    ãĥ³ãĤ¹
    -0.07
    atric
    -0.07
    POSITIVE LOGITS
    ยà¹Īà¸Ń
    0.07
    ìłĢ
    0.07
    adia
    0.07
    cium
    0.06
    -ci
    0.06
    -même
    0.06
    èģĮå®Ī
    0.06
     же
    0.06
    atter
    0.06
    arton
    0.06
    Activations Density 0.485%

    No Known Activations