© 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. 14178
    Prev
    Next
    INDEX
    Explanations

    non-English characters

    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
    åĢĻ
    -0.31
    ard
    -0.23
    ress
    -0.22
    er
    -0.21
    om
    -0.21
    -ish
    -0.20
    ẻ
    -0.20
    åIJİ
    -0.20
    ek
    -0.20
    侯
    -0.20
    POSITIVE LOGITS
    ä¿¡èµĸ
    0.29
    羣è¯ļ
    0.25
     danmark
    0.24
    ÑĢай
    0.23
     amatør
    0.23
    æIJºæīĭ
    0.22
     erotisk
    0.22
    åħ±åĪĽ
    0.21
    æ¯ıä¸Ģä½į
    0.21
     Geile
    0.21
    Activations Density 0.124%

    No Known Activations