© 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. 11557
    Prev
    Next
    INDEX
    Explanations

    same day or year

    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
    USES
    -0.20
    £¼
    -0.19
    wig
    -0.18
    两åij¨
    -0.18
     Hog
    -0.18
    gil
    -0.18
     bi
    -0.18
    è¿Ļåĩłå¤©
    -0.17
    è¿Ļ段æŶéĹ´
    -0.17
     weeks
    -0.17
    POSITIVE LOGITS
    åĸı
    0.17
    IndexChanged
    0.17
    (internal
    0.17
    å´ĩé«ĺ
    0.17
     rá»Ŀi
    0.17
    aten
    0.17
    rapper
    0.17
    .Formatter
    0.16
    åħħ足çļĦ
    0.16
    çĿĩ
    0.16
    Activations Density 0.018%

    No Known Activations