© 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. 14864
    Prev
    Next
    INDEX
    Explanations

    numbers denoting counts

    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
    _ISO
    -0.21
     OR
    -0.21
    åħ¨å®¶
    -0.21
    æĹłæķ°æ¬¡
    -0.21
    å¤ļ次
    -0.20
     ISO
    -0.19
     Iso
    -0.19
    çĿ£ä¿ĥ
    -0.19
    ä¸Ģ次次
    -0.19
     дл
    -0.19
    POSITIVE LOGITS
    åIJįåįķ
    0.24
     заÑĢегиÑģÑĤ
    0.22
     fewer
    0.21
     roster
    0.21
    åIJįé¢Ŀ
    0.21
    符åIJĪæĿ¡ä»¶
    0.20
    ãģĦãĤĭ
    0.19
    人éĢī
    0.19
     Coke
    0.19
    å£
    0.19
    Activations Density 0.057%

    No Known Activations