© 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. 14559
    Prev
    Next
    INDEX
    Explanations

    years, season, past times

    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
    çŀ³
    -0.25
    há»ķ
    -0.23
    ToObject
    -0.22
    hợ
    -0.22
     fetisch
    -0.22
    说èĩªå·±
    -0.21
    ä¸ĢåIJ¬
    -0.20
     Geile
    -0.20
     pornost
    -0.20
    esture
    -0.20
    POSITIVE LOGITS
    ä»Ĭå¹´
    0.31
    è¿Ļä¸Ģå¹´
    0.28
    åľ¨ä»Ĭå¹´
    0.26
    åħ¨å¹´
    0.26
    åIJĮæ¯Ķ
    0.26
     season
    0.26
    åݻ年
    0.25
    å¹´åĪĿ
    0.25
     drought
    0.25
    æ°ĶåĢĻ
    0.25
    Activations Density 0.038%

    No Known Activations