© 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. 12690
    Prev
    Next
    INDEX
    Explanations

    Tahiti, Polynesian, Tahitian

    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
     UNUSED
    -0.20
    chen
    -0.20
    uum
    -0.18
    诤
    -0.18
    alties
    -0.18
    ews
    -0.18
    éĻķ西
    -0.18
    è¹Ń
    -0.17
    anj
    -0.17
    ried
    -0.17
    POSITIVE LOGITS
    æĹıèĩªæ²»åİ¿
    0.20
    cope
    0.19
    éģ¨
    0.19
    Ng
    0.18
    .googleapis
    0.18
    ãĤ«ãĥ³
    0.18
    .AddItem
    0.18
     BIND
    0.17
    Mos
    0.17
     moc
    0.17
    Activations Density 0.006%

    No Known Activations