© 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. 12841
    Prev
    Next
    INDEX
    Explanations

    Washington Redskins and Nationals

    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
    è·µ
    -0.17
    æļ¹
    -0.17
    ÐIJÐĿ
    -0.16
    let
    -0.16
    俦
    -0.16
    级以ä¸Ĭ
    -0.16
     Scot
    -0.16
    éļ¾åħ³
    -0.16
    oes
    -0.16
    å±ij
    -0.16
    POSITIVE LOGITS
    rup
    0.21
    rp
    0.19
    gether
    0.18
    iation
    0.17
    rit
    0.17
    rush
    0.17
    naire
    0.17
    wards
    0.17
    ICH
    0.17
    eter
    0.17
    Activations Density 0.003%

    No Known Activations