© 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. 14162
    Prev
    Next
    INDEX
    Explanations

    saints' names

    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
    çīµæĮĤ
    -0.20
    åĢ¾
    -0.19
    rost
    -0.19
    åĤ¾
    -0.18
    èĬ¥
    -0.18
    enson
    -0.18
    gli
    -0.18
    åĸ·æ¶Ĥ
    -0.18
    herit
    -0.18
    足以
    -0.18
    POSITIVE LOGITS
    çĶ»åĥı
    0.21
    asar
    0.21
    娶
    0.20
     Gale
    0.19
    iard
    0.19
    çĭ¬ç«ĭ
    0.19
    æIJŃ
    0.18
    wife
    0.18
    è¡Ĺ
    0.18
    _nat
    0.18
    Activations Density 0.015%

    No Known Activations