© 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. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12011
    Prev
    Next
    INDEX
    Explanations

    monetary awards

    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
    æİĴéĺŁ
    -0.23
    åĽ½å®¶éĺŁ
    -0.21
    æĿł
    -0.21
     ÑģебÑı
    -0.20
    ä»»ä½ķæŶåĢĻ
    -0.20
    MDB
    -0.19
    urg
    -0.19
     vat
    -0.19
    æİĴæĶ¾
    -0.19
    åĩłä¹İæĺ¯
    -0.19
    POSITIVE LOGITS
    VES
    0.22
    _each
    0.19
    uben
    0.19
     essay
    0.19
    each
    0.19
    æ¯ıä½į
    0.18
    æİĪ
    0.18
    -ves
    0.18
    æį»
    0.18
    elocity
    0.18
    Activations Density 0.013%

    No Known Activations