© 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. 10729
    Prev
    Next
    INDEX
    Explanations

    bleeding, bleach, bleacher

    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
    iveness
    -0.18
    åŁİå¸Ĥ群
    -0.18
    ¡
    -0.18
    æ¨Ĺ
    -0.17
    oner
    -0.16
    åŃIJéĩĮ
    -0.16
    èĩ¾
    -0.15
    arians
    -0.15
    æŀķ头
    -0.15
    åļı
    -0.15
    POSITIVE LOGITS
    çĦ¶æĺ¯
    0.18
    å¤ł
    0.16
    backs
    0.16
    itt
    0.15
    hari
    0.14
    headed
    0.14
    thora
    0.14
    éĵ§
    0.14
     Moff
    0.14
    æ±
    0.14
    Activations Density 0.012%

    No Known Activations