© 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. 14608
    Prev
    Next
    INDEX
    Explanations

    looking into

    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
    座è°Ī
    -0.18
     rap
    -0.17
    anager
    -0.17
    çݯå¢ĥä¸ĭ
    -0.17
    åĩĨ
    -0.17
    onen
    -0.17
    åĮº
    -0.17
    çݯå¢ĥ
    -0.17
    宿
    -0.17
    çİ°åľº
    -0.17
    POSITIVE LOGITS
    æѤäºĭ
    0.30
    _OC
    0.19
    æĺ¯åIJ¦åŃĺåľ¨
    0.19
    åħ¶å®ĥéĹ®é¢ĺ
    0.19
    hec
    0.18
    æĺ¯åIJ¦æľī
    0.18
    人åĵ¡
    0.18
    æł¸å®ŀ
    0.17
    åĪ°åºķæĺ¯
    0.17
    人士
    0.17
    Activations Density 0.016%

    No Known Activations