© 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. 16662
    Prev
    Next
    INDEX
    Explanations

    nice people

    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
    èĽĻ
    -0.21
    è¿Ń
    -0.21
    è¢ĸ
    -0.20
    èħ¾é£ŀ
    -0.20
    нов
    -0.20
    åIJ¬è¯¾
    -0.20
    æİĮæݧ
    -0.20
    壮è§Ĥ
    -0.20
    auty
    -0.19
    è¿«ä¸įåıĬ
    -0.19
    POSITIVE LOGITS
    åĸĦèī¯
    0.33
    好人
    0.25
     nature
    0.21
    åı¯ä¿¡
    0.21
     gentle
    0.20
    åĵģå¾·
    0.20
     bene
    0.20
    çļĦ人éĥ½
    0.20
    模èĮĥ
    0.20
    nature
    0.19
    Activations Density 0.039%

    No Known Activations