© 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. 15536
    Prev
    Next
    INDEX
    Explanations

    numbers followed by other numbers or symbols

    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
    èIJ¥åķĨ
    -0.23
    	ext
    -0.20
    ophon
    -0.20
    eenth
    -0.20
    泡泡
    -0.19
    eer
    -0.19
    åľ¬
    -0.18
    à¹Ĩ
    -0.18
    ä¸ĩ象
    -0.18
    ä¹Łä¸įéĶĻ
    -0.18
    POSITIVE LOGITS
    umph
    0.23
    ke
    0.20
    å¾Ĺ
    0.19
    w
    0.19
    h
    0.19
    æİĴ
    0.18
    -ton
    0.18
    ĥģ
    0.18
     expected
    0.18
    phys
    0.18
    Activations Density 0.021%

    No Known Activations