© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 12491
    Prev
    Next
    INDEX
    Explanations

    first, second, third half, quarter, inning

    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
    QB
    -0.21
    éĢĤ
    -0.20
    stry
    -0.19
     пÑĢиÑıÑĤн
    -0.19
    ophobia
    -0.19
    主åĬ¨
    -0.18
    éĩįè§Ĩ
    -0.18
     Dah
    -0.18
    åħ¶æīĢ
    -0.18
     ÐĴо
    -0.18
    POSITIVE LOGITS
    æĹ¶æ®µ
    0.22
    污æŁĵéĺ²æ²»
    0.20
    éĤ£æ®µ
    0.20
    Rendering
    0.20
    çĹħä¾ĭ
    0.19
    使çĶ¨ç¶²è·¯
    0.19
    ãĤ±ãĥ¼ãĤ¹
    0.19
    èĬĤ课
    0.19
     slack
    0.18
    è¿Ļ个游æĪı
    0.18
    Activations Density 0.014%

    No Known Activations