© 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. 16525
    Prev
    Next
    INDEX
    Explanations

    however, though

    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
     Burl
    -0.22
    çĨŁ
    -0.21
    çĨŁæĤī
    -0.20
    åĩĮ
    -0.20
    ç»ı
    -0.20
    lash
    -0.19
    ç»ıå¼Ģ
    -0.19
    æ´ª
    -0.19
    establish
    -0.18
    ä¸ī人
    -0.18
    POSITIVE LOGITS
    è¿Ļä¸ĢçĤ¹
    0.22
    åħ¶å®ĥéĹ®é¢ĺ
    0.20
    è¿ĻçĤ¹
    0.20
    æ¯ķç«Ł
    0.19
     ведÑĮ
    0.19
    æijŀ
    0.19
    æ¤Ł
    0.18
    --[[
    0.18
     однако
    0.18
    è¹¼
    0.18
    Activations Density 0.053%

    No Known Activations