© 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. 14274
    Prev
    Next
    INDEX
    Explanations

    unveiled new plans

    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
    ãĥŃãĥ¼
    -0.19
    èĩªè´Ł
    -0.17
     xuyên
    -0.17
    .HashSet
    -0.17
     Nähe
    -0.17
    ÑĤеÑĢ
    -0.17
    çªģåĩºéĹ®é¢ĺ
    -0.16
    /to
    -0.16
     giá»ıi
    -0.16
    lices
    -0.16
    POSITIVE LOGITS
    äº®çĽ¸
    0.23
    æĪIJæŀľ
    0.19
     ÑģÑĤоим
    0.19
    rabbit
    0.19
    atal
    0.18
    ä¼Ĭå§ĭ
    0.18
    å®ıä¼Ł
    0.18
    è¯ļæĦı
    0.17
    ee
    0.17
    æĸ°è½¦
    0.17
    Activations Density 0.014%

    No Known Activations