© 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. 14657
    Prev
    Next
    INDEX
    Explanations

    NA, ALL, XXXX, =, NULL, Server, child, Not

    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
    spy
    -0.18
    anel
    -0.18
    aving
    -0.18
     punct
    -0.18
    ÙĨÙħ
    -0.18
    -footer
    -0.17
    模èĮĥ
    -0.17
    urses
    -0.17
    lek
    -0.17
    -stars
    -0.17
    POSITIVE LOGITS
    çĽĶ
    0.23
    æĪĸå¤ļ
    0.22
    æĪĸæĺ¯
    0.21
     carn
    0.20
    è¿·èĮ«
    0.19
    ç¹ģå¿Ļ
    0.18
    æĪĺåĽ½
    0.18
    èī¯æĢ§
    0.18
    æĿĥå¨ģ
    0.18
    ÑģÑĥд
    0.18
    Activations Density 0.477%

    No Known Activations