© 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. 15428
    Prev
    Next
    INDEX
    Explanations

    leather products and accessories

    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
    åĿŁ
    -0.24
    è°·çĪ±
    -0.19
    rug
    -0.18
    èĽ®
    -0.18
    Tac
    -0.18
     Lives
    -0.18
     slic
    -0.18
    #aa
    -0.17
    ä¸įåĥı
    -0.17
     Sanford
    -0.17
    POSITIVE LOGITS
    带æľī
    0.19
    æĪ´
    0.19
    æ³½
    0.19
    对çħ§
    0.19
    æĪ´çĿĢ
    0.18
    åĥ®
    0.18
    éĸĭ
    0.18
    èľ·
    0.18
    æĸĩèīº
    0.18
     å¼Ģ
    0.17
    Activations Density 0.012%

    No Known Activations