© 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. 11444
    Prev
    Next
    INDEX
    Explanations

    imported or implied

    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
    ç»Ī
    -0.20
     pillars
    -0.19
    éĤ¦
    -0.19
    åħ³æ³¨
    -0.19
    ount
    -0.19
     banc
    -0.18
     Pont
    -0.18
    /uploads
    -0.18
    çĤ¹
    -0.18
    åIJĽ
    -0.18
    POSITIVE LOGITS
    è°ĥéħį
    0.22
    åľ¨æĹ¥æľ¬
    0.20
    çĶŁäº§åĴĮ
    0.20
    ä»İ严
    0.19
    ä¸ŃåĽ½å¤§éĻĨ
    0.19
    æĺ¯éŁ©åĽ½
    0.19
     маÑĤеÑĢиал
    0.19
    å¤ļä¸ªåĽ½å®¶
    0.18
    åľ¨è¿ĩ渡
    0.18
    äº§åľ°
    0.17
    Activations Density 0.001%

    No Known Activations