© 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. 14804
    Prev
    Next
    INDEX
    Explanations

    Beowulf, Brothers Karamazov, Shakespeare

    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
    ä¸įä¸ĭ
    -0.20
    éļ¶
    -0.20
    perm
    -0.20
    ä¸įå°ıå¿ĥ
    -0.20
     stom
    -0.20
     ÑģоÑħÑĢани
    -0.19
    害ç¾ŀ
    -0.19
    è¾ĥ大
    -0.19
    .dom
    -0.19
    æ¼Ķ
    -0.19
    POSITIVE LOGITS
    alte
    0.23
    igram
    0.20
    ilogy
    0.19
     beg
    0.18
    åĨįåĪ°
    0.18
    éĵ¸
    0.17
    âĪĸ
    0.17
     %#
    0.17
    忳
    0.17
    :right
    0.17
    Activations Density 0.028%

    No Known Activations