© 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. 13856
    Prev
    Next
    INDEX
    Explanations

    days a week

    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
    ÑĢаÐ
    -0.21
    strup
    -0.18
    们éĥ½
    -0.17
    ised
    -0.17
    orta
    -0.17
    æĿł
    -0.17
    å¹´éĹ´
    -0.17
    åĩłå®¶
    -0.17
    å¾Ģäºĭ
    -0.17
    å¢Ļä½ĵ
    -0.17
    POSITIVE LOGITS
     Moff
    0.21
    amburger
    0.18
    ingu
    0.17
    един
    0.17
    gent
    0.17
     обÑģлÑĥж
    0.17
    оÑĩка
    0.17
    éĶ»
    0.16
    Matchers
    0.16
     Hat
    0.16
    Activations Density 0.003%

    No Known Activations