© 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. 11939
    Prev
    Next
    INDEX
    Explanations

    `.c` or `.h` file extensions

    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
    .shopping
    -0.25
     sourceMapping
    -0.24
     fkk
    -0.24
    imet
    -0.22
    akter
    -0.22
    uters
    -0.22
    تÙĪج
    -0.21
    åļĨ
    -0.21
    -suite
    -0.21
    ogi
    -0.21
    POSITIVE LOGITS
    #ifdef
    0.28
    -&
    0.26
    _##
    0.26
     ÐIJлекÑģан
    0.25
    ->
    0.25
    ä¹Łè¦ģ
    0.24
    æł¸å¿ĥ
    0.23
     ÐŁÐ¾Ñĩем
    0.23
     FIXME
    0.23
    è¨ĺäºĭ
    0.22
    Activations Density 1.662%

    No Known Activations