© 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. 15488
    Prev
    Next
    INDEX
    Explanations

    publication details and dates

    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
     ÐŁÐ¾Ñĩем
    -0.27
    à¹Ģà¸Ĺà¸Ħà¹Ĥà¸Ļ
    -0.23
    à¸Ħà¸ĵะà¸ģรรม
    -0.22
     PaÅĦstwo
    -0.22
     Erotische
    -0.21
     à¸ŀฤษ
    -0.21
     ÐĶмиÑĤÑĢ
    -0.21
    estre
    -0.21
    à¹Ĥรà¸ĩà¸ŀยา
    -0.20
     ÐIJлекÑģан
    -0.20
    POSITIVE LOGITS
    ãĤ¿ãĤ¤ãĥĹ
    0.21
    丢äºĨ
    0.19
     fkk
    0.19
    çĥ¹
    0.19
     pubs
    0.19
    æĸĩçĮ®
    0.19
     Contributions
    0.18
    ovel
    0.18
     scient
    0.17
    ä¸Ĭå¹´
    0.17
    Activations Density 0.008%

    No Known Activations