© 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. 14872
    Prev
    Next
    INDEX
    Explanations

    at this time or point

    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
    æĹłæķ°æ¬¡
    -0.22
    æ¾Į
    -0.20
    åģļäºĭ
    -0.19
    å¤ļ次
    -0.18
     Fal
    -0.18
     subsequent
    -0.17
     recurring
    -0.17
     blind
    -0.17
    å¦ĤæľŁ
    -0.17
    以人æ°ij为
    -0.17
    POSITIVE LOGITS
     Clair
    0.23
    jab
    0.21
    abouts
    0.21
    æѤåĪ»
    0.20
    éĺ¶æ®µ
    0.20
    ŀæĢ§
    0.19
    æľīä»»ä½ķ
    0.19
    	TokenName
    0.19
    niejs
    0.19
    è¿ĺä¸įæĺ¯
    0.19
    Activations Density 0.023%

    No Known Activations