© 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. 13782
    Prev
    Next
    INDEX
    Explanations

    is becomes or has been

    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
     пÑĥÑĤеÑĪ
    -0.26
     поÑģколÑĮ
    -0.23
     ÐIJлекÑģан
    -0.23
    ä»İå°ı
    -0.23
     моÑīн
    -0.22
     пÑĢиÑıÑĤн
    -0.21
    íĹĢ
    -0.21
     ÑĢÑĥков
    -0.20
     ÐĶмиÑĤÑĢ
    -0.20
     наÑĢко
    -0.20
    POSITIVE LOGITS
    ä¸į容
    0.26
     Thá»ĥ
    0.20
    _FRONT
    0.20
    è°ģçŁ¥éģĵ
    0.19
    _CONST
    0.19
    颤
    0.19
    æŁ³
    0.19
    _pulse
    0.19
    æ¥ļ
    0.19
    stdafx
    0.18
    Activations Density 0.231%

    No Known Activations