© 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. 14504
    Prev
    Next
    INDEX
    Explanations

    this year

    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
    è¿ijäºĽå¹´
    -0.27
    ä»ĬåĽŀ
    -0.25
    æŃ¤æ¬¡
    -0.25
    æľ¬æ¬¡
    -0.24
    ä»ĬåĽŀãģ¯
    -0.23
    æľ¬æ¬¡äº¤æĺĵ
    -0.22
    ä»ĬåĽŀãģ®
    -0.21
    åĪ°æľĢåIJİ
    -0.20
    è¿ijäºĽ
    -0.20
    å½ĵæĻļ
    -0.20
    POSITIVE LOGITS
    为æŃ¢
    0.27
    abouts
    0.25
    à¹ģหละ
    0.23
    cline
    0.19
    ÅĦ
    0.19
    yme
    0.18
    èĸ¤
    0.18
    ç¨į
    0.18
    æīįåıijçİ°
    0.18
    -Oct
    0.17
    Activations Density 0.032%

    No Known Activations