© 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. 12061
    Prev
    Next
    INDEX
    Explanations

    dates in the format Day, Month

    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
    åħ¶ä¸Ńæľī
    -0.20
    èĢĮæĪIJ
    -0.20
    ฯ
    -0.20
    å¹¶åľ¨
    -0.20
    ios
    -0.19
    set
    -0.18
     imperson
    -0.18
    æīĢä»¥åľ¨
    -0.18
    并ä¸İ
    -0.18
    ers
    -0.18
    POSITIVE LOGITS
    esterday
    0.21
    _published
    0.21
    æ»ĭåħ»
    0.19
    _padding
    0.19
    对äºİæĪij们
    0.18
    好åĩłä¸ª
    0.18
    üler
    0.18
    çĤ¹æ»´
    0.18
    émon
    0.18
    è·ĥ
    0.18
    Activations Density 0.015%

    No Known Activations