© 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. 13944
    Prev
    Next
    INDEX
    Explanations

    hereinafter followed by definition

    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
    tier
    -0.20
    aroo
    -0.19
    æĸ¹éĿ¢
    -0.18
    çļĦèĥĮåIJİ
    -0.18
    æģĻ
    -0.17
    å½ĵåĪĿ
    -0.17
    scribe
    -0.17
    åľ¨è¿ĩæ¸¡æľŁ
    -0.17
    çİ°åľ¨å·²ç»ı
    -0.17
    们çļĦ
    -0.17
    POSITIVE LOGITS
    æıIJåĪ°
    0.21
    elon
    0.20
    edly
    0.20
    ç®Ģ称
    0.20
    åIJIJ
    0.20
    å¯Ĥ
    0.19
    以ä¸ĭç®Ģ称
    0.19
    äººæł¼
    0.19
    ocket
    0.19
    称
    0.19
    Activations Density 0.047%

    No Known Activations