© 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. 10698
    Prev
    Next
    INDEX
    Explanations

    Jr. Inc. .m .o titles

    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
    berra
    -0.22
    æѤ
    -0.21
    æķ´ä¸ª
    -0.20
    à¸Ĥà¸Ļา
    -0.20
    à¹Ģà¸Ĺà¸Ħà¹Ĥà¸Ļ
    -0.19
    wright
    -0.19
    à¸Ħà¸ĵะà¸ģรรม
    -0.19
    æµ´
    -0.19
    çĹķ
    -0.18
    สามาร
    -0.18
    POSITIVE LOGITS
    à¹Į
    0.36
    ï¸ı
    0.32
    Ùĭ
    0.27
    .,
    0.25
    åħĴ
    0.24
    Âł
    0.23
    Ùij
    0.23
    \:
    0.23
    0.21
    ÙIJ
    0.20
    Activations Density 0.900%

    No Known Activations