© 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. 13624
    Prev
    Next
    INDEX
    Explanations

    email and addresses

    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
    ipy
    -0.20
    transform
    -0.20
     unp
    -0.19
    èķĪ
    -0.19
    sold
    -0.19
    æĤ±
    -0.19
    ulum
    -0.18
    rh
    -0.18
    å¥ı
    -0.18
    ì²Ļ
    -0.18
    POSITIVE LOGITS
    éĤ®ç®±
    0.29
    åŁŁåIJį
    0.23
     email
    0.23
    çĶµåŃIJéĤ®ä»¶
    0.22
    è´¢
    0.22
    .gmail
    0.22
     Gmail
    0.21
    éģ¨
    0.21
    è´¦åı·
    0.21
    _SUFFIX
    0.20
    Activations Density 0.023%

    No Known Activations