© 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. 14843
    Prev
    Next
    INDEX
    Explanations

    weekend events

    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
     bypass
    -0.22
    Dst
    -0.22
    ä¸įèĥ½åĨį
    -0.19
    年以ä¸Ĭ
    -0.19
     reminis
    -0.19
    åįĬå¹´
    -0.19
    æ¯ıæľĪ
    -0.19
     Rated
    -0.18
    ÑĥпиÑĤÑĮ
    -0.18
    ìĹĨ
    -0.18
    POSITIVE LOGITS
    两天
    0.28
    第ä¸Ģ天
    0.28
    第äºĮ天
    0.26
    èĨ³
    0.24
    ä¸Ģå¤ľ
    0.23
    åħ¨å¤©
    0.23
    å³°åĢ¼
    0.23
    ä¸Ģ天
    0.22
    ä¸ī天
    0.20
    è¿Ļ两天
    0.20
    Activations Density 0.056%

    No Known Activations