© 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. 13007
    Prev
    Next
    INDEX
    Explanations

    functions applications future packages perceptions

    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
    å¦Ĥæŀľè¯´
    -0.24
    æĪĸèĢħ说
    -0.23
    好好
    -0.22
     remot
    -0.22
    éĢļè¿ĩ对
    -0.20
    好å¤ļ
    -0.19
    ä¸įä»ħä»ħ
    -0.19
    æĦıæĢĿæĺ¯
    -0.19
    ãģĭãĤĤãģĹãĤĮãģ¾ãģĽãĤĵãģĮ
    -0.18
     _______,
    -0.18
    POSITIVE LOGITS
    amina
    0.20
    SWG
    0.19
    裾
    0.18
    lek
    0.18
    oice
    0.18
    DDR
    0.18
    SSF
    0.18
    æĢ§ä»·
    0.18
    LOAT
    0.17
    éĻIJ度
    0.17
    Activations Density 0.078%

    No Known Activations