© 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. 19367
    Prev
    Next
    INDEX
    Explanations

    image markdown syntax

    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
    #create
    -0.07
    çŃĭ骨
    -0.07
    ffer
    -0.06
    ages
    -0.06
    onse
    -0.06
    _EXIST
    -0.06
    æľĪçĶŁ
    -0.06
    èĩªçĦ¶ä¸įä¼ļ
    -0.06
     consci
    -0.06
    udu
    -0.06
    POSITIVE LOGITS
    oul
    0.07
    転
    0.07
    thumb
    0.07
    .defineProperty
    0.07
     margin
    0.07
    rench
    0.07
    Margin
    0.07
    oin
    0.07
    margin
    0.07
    thumbnails
    0.07
    Activations Density 0.025%

    No Known Activations