© 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. 11763
    Prev
    Next
    INDEX
    Explanations

    linguistic, linguist, linguistics

    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
    åŃIJéĩĮ
    -0.20
    çIJ®
    -0.19
    çºłæŃ£
    -0.18
    adm
    -0.17
    rise
    -0.17
    казан
    -0.17
    enger
    -0.16
    ter
    -0.16
    åŃļ
    -0.15
    ign
    -0.15
    POSITIVE LOGITS
    æĺİæľĹ
    0.19
    stile
    0.19
    èĵŁ
    0.18
    é©®
    0.18
    ä¸ĭ乡
    0.17
    antz
    0.16
    ledged
    0.16
    es
    0.16
    rary
    0.16
    eurs
    0.16
    Activations Density 0.008%

    No Known Activations