© 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. 16642
    Prev
    Next
    INDEX
    Explanations

    dates or numbers

    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
    æįĮ
    -0.21
    æķıæĦŁ
    -0.19
    毡
    -0.19
    åIJ¼
    -0.18
    омеÑĢ
    -0.18
    Partner
    -0.18
    çģĮ
    -0.18
    NSNotification
    -0.17
     partner
    -0.17
     HARD
    -0.17
    POSITIVE LOGITS
    ispers
    0.21
    æ°ijå¿ĥ
    0.20
    许
    0.20
    è·ŁçĿĢ
    0.19
    éĿĴæĺ¥
    0.19
    actory
    0.19
    è·Łè¿Ľ
    0.18
    ãģ¨ãĤĬ
    0.18
    olume
    0.18
    ä¸ĢçĤ¹çĤ¹
    0.18
    Activations Density 0.115%

    No Known Activations