© 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. 49573
    Prev
    Next
    INDEX
    Explanations

    /* comments and directives

    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
    esis
    -0.09
    ities
    -0.08
    <<<<<<<
    -0.08
    -vous
    -0.08
    abouts
    -0.07
    nable
    -0.07
    pite
    -0.07
    ifest
    -0.07
    çļĦ好åıĭ
    -0.07
    rau
    -0.07
    POSITIVE LOGITS
    à¹īม
    0.10
    ़
    0.09
    Úº
    0.08
    aná
    0.08
    an
    0.08
    æľī
    0.08
    IJ
    0.08
    ìį¨
    0.08
    =*/
    0.08
    à¸ģารà¸Īัà¸Ķà¸ģาร
    0.07
    Activations Density 0.039%

    No Known Activations