© 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. 13816
    Prev
    Next
    INDEX
    Explanations

    try seeing if

    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
    æĬĺ
    -0.23
    owell
    -0.19
    èĸ¨
    -0.18
    OI
    -0.18
    nte
    -0.18
    æĪijåĸľæ¬¢
    -0.18
    ä¸Ńå¤ĸ
    -0.18
    .sharedInstance
    -0.18
    è°Ĩ
    -0.17
     Desert
    -0.17
    POSITIVE LOGITS
    è¯ķè¯ķ
    0.38
    æĺ¯åIJ¦æľī
    0.35
    æĺ¯åIJ¦åŃĺåľ¨
    0.35
    å°Ŀè¯ķ
    0.33
    çľĭçľĭ
    0.31
    说ä¸įå®ļ
    0.30
    æ£ĢæŁ¥
    0.30
    ä¼ļä¸įä¼ļ
    0.30
    æľī没æľī
    0.29
    æİĴæŁ¥
    0.29
    Activations Density 0.095%

    No Known Activations