© 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. 14553
    Prev
    Next
    INDEX
    Explanations

    problems or difficulty

    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
    iban
    -0.20
    们éĥ½
    -0.19
    å»Ĭ
    -0.18
    å·²ç»ıåľ¨
    -0.18
    أخبار
    -0.18
    że
    -0.18
    ä¸įçķĻ
    -0.17
    å·²æľī
    -0.17
    пÑĢакÑĤик
    -0.17
     BAS
    -0.17
    POSITIVE LOGITS
    éĺħ读
    0.19
    åħ¨æĸĩ
    0.18
    chn
    0.18
    _EV
    0.18
    ä¸Ĭç½ij
    0.18
    ä¸įåı¯éģ¿åħį
    0.18
    mailto
    0.18
    çĵ¶é¢Ī
    0.18
    ä¸į便
    0.17
    æ¢Ĩ
    0.17
    Activations Density 0.006%

    No Known Activations