© 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. 11899
    Prev
    Next
    INDEX
    Explanations

    image files and technical apparatus

    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
    ä¸įåĥı
    -0.19
    Ini
    -0.18
    åķ¸
    -0.17
     Washing
    -0.17
    鸡汤
    -0.17
    atform
    -0.17
    aris
    -0.17
    æ¸Į
    -0.17
    èŀįåªĴä½ĵ
    -0.17
    æ´Ĺ
    -0.17
    POSITIVE LOGITS
    chr
    0.17
    åħ·ä½ĵ
    0.17
    æĬĢæľ¯åĴĮ
    0.17
    èĢģ大
    0.17
     ÑģÑĥд
    0.17
     pit
    0.17
    åħļ
    0.17
    ä»
    0.17
    çIJĨ
    0.16
     ActiveSupport
    0.16
    Activations Density 0.380%

    No Known Activations