© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15119
    Prev
    Next
    INDEX
    Explanations

    cooling and what is cooled

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-14b-saes/saes_Qwen_Qwen3-14B_batch_top_k/resid_post_layer_20
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ially
    -0.20
    ðŁı»
    -0.19
    iker
    -0.18
    getter
    -0.18
    ruc
    -0.17
    æĢ§åĴĮ
    -0.17
    ively
    -0.17
    ä¸Ģå®ļç¨ĭ度
    -0.17
     Airways
    -0.17
    ikers
    -0.17
    POSITIVE LOGITS
    èļ±
    0.20
    tower
    0.19
    æݪæĸ½
    0.18
    icine
    0.17
    reso
    0.17
    设æĸ½
    0.17
    stuff
    0.17
    ä½ĵç³»
    0.16
     Sage
    0.16
    ä¸ĭæĿ¥çļĦ
    0.16
    Activations Density 0.011%

    No Known Activations