© 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. 11421
    Prev
    Next
    INDEX
    Explanations

    Search Afropunk.com

    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
    æĮİ
    -0.20
    illy
    -0.20
    irit
    -0.19
     Aç
    -0.18
    è·¨
    -0.18
    纫
    -0.18
    çĵ
    -0.18
    å°Ħ
    -0.18
    å¨ħ
    -0.18
     xuyên
    -0.18
    POSITIVE LOGITS
    注
    0.19
     bol
    0.19
    åij¨æľ«
    0.18
     loos
    0.18
    è´¢
    0.18
    ISE
    0.17
    æĮ
    0.17
     Heller
    0.17
     abst
    0.17
    rome
    0.17
    Activations Density 0.009%

    No Known Activations