© 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. 10901
    Prev
    Next
    INDEX
    Explanations

    Society of

    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
    inations
    -0.18
    imon
    -0.17
    oes
    -0.16
    åľ°å¸¦
    -0.16
    Ĵ
    -0.16
    èĢģ人家
    -0.15
    ä¼ĬåĪ©
    -0.15
    åħµåĽ¢
    -0.15
    onium
    -0.15
    ÑĤек
    -0.15
    POSITIVE LOGITS
    wide
    0.25
    -wide
    0.24
    æĦī
    0.18
    ships
    0.17
    æĭ¢
    0.17
    UnderTest
    0.17
    -minded
    0.17
    azzi
    0.17
    ware
    0.16
    éļĪ
    0.16
    Activations Density 0.019%

    No Known Activations