© 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. 15567
    Prev
    Next
    INDEX
    Explanations

    hypothetical or uncertain possibility

    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
    åĵĩ
    -0.20
    elta
    -0.19
    ä¹ĥæĺ¯
    -0.19
    baugh
    -0.19
    adal
    -0.18
    累累
    -0.18
     viá»ĩc
    -0.18
    ited
    -0.18
    леж
    -0.18
    ible
    -0.17
    POSITIVE LOGITS
     saja
    0.20
    ÑĩиÑģлен
    0.20
    <Scalars
    0.20
    -être
    0.19
    -times
    0.18
    åĪ«çļĦ
    0.18
    æĺ¯åľ¨
    0.18
    ìĶ©
    0.17
    åĩł
    0.17
    times
    0.17
    Activations Density 0.019%

    No Known Activations