© 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. 24674
    Prev
    Next
    INDEX
    Explanations

    relation between

    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
    elig
    -0.10
    elman
    -0.10
    nite
    -0.09
    oku
    -0.08
    reon
    -0.08
    regon
    -0.08
    erman
    -0.08
    ictured
    -0.07
    innacle
    -0.07
    rella
    -0.07
    POSITIVE LOGITS
    ationship
    0.09
    áŁĭ
    0.09
    ional
    0.09
    ervoir
    0.08
    ities
    0.08
    åĴĮä¹īåĬ¡
    0.08
    <|box_end|>
    0.08
    à§įস
    0.07
     chặt
    0.07
    å¾Ģ常ä¸Ģæł·
    0.07
    Activations Density 0.093%

    No Known Activations