© 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. 15660
    Prev
    Next
    INDEX
    Explanations

    dates and times

    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
    à¸Ħà¸ĵะà¸ģรรม
    -0.23
     ÐIJлекÑģан
    -0.23
    à¹Ģà¸Ĺà¸Ħà¹Ĥà¸Ļ
    -0.22
    à¸Ńำà¸Ļวยà¸Ħวาม
    -0.22
    à¸Ļà¹Ĥย
    -0.21
    feat
    -0.20
    ammers
    -0.20
    à¸Ħะà¹ģà¸Ļ
    -0.20
     меÑĢоп
    -0.19
    à¹Ĥรà¸ĩà¸ŀยา
    -0.19
    POSITIVE LOGITS
    æ´ĹèĦ¸
    0.21
    注æĺİåĩºå¤Ħ
    0.21
    æĥ³è¿ĩ
    0.21
    æĮ¹
    0.20
    (vertical
    0.20
    æ£Ģç´¢
    0.20
    TimeInterval
    0.19
    主治
    0.18
    读åIJİ
    0.18
    åĩºå¤Ħ
    0.18
    Activations Density 0.022%

    No Known Activations