© 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. 16307
    Prev
    Next
    INDEX
    Explanations

    counts or lists following headings

    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
    ursive
    -0.21
    åĨį说
    -0.20
    iples
    -0.19
    ould
    -0.18
     Vent
    -0.18
    iten
    -0.18
    IVEN
    -0.18
    éģ¿
    -0.18
    oucher
    -0.17
    仲
    -0.17
    POSITIVE LOGITS
    loff
    0.22
    æŁIJç§įç¨ĭ度
    0.21
    Ø·ÙĬ
    0.20
    ç®Ģåįķ
    0.20
    æ¤Ĵ
    0.19
    å¤ĸåľ°
    0.19
    讨åİĮ
    0.19
    æ¯ı次éĥ½
    0.19
    ç³ł
    0.19
    {text
    0.18
    Activations Density 0.124%

    No Known Activations