© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-14B
    5. 20-RESID-BATCHTOPK-65K__L0-80
    7. 15403
    Prev
    Next
    INDEX
    Explanations

    so much

    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
    æĸ°éĹ»åıijå¸ĥ
    -0.20
    rix
    -0.20
    ä¸įå¤ļ
    -0.18
    cust
    -0.18
     cust
    -0.18
     Animated
    -0.18
    为广大
    -0.18
    æŃ£æĺ¯åĽłä¸º
    -0.17
     Holl
    -0.17
    çĸ²åĬ³
    -0.17
    POSITIVE LOGITS
     ÐĴедÑĮ
    0.23
     ведÑĮ
    0.22
    Oi
    0.21
    好äºĨ
    0.19
    ãģ®ãģ§ãģĻãģĮ
    0.19
    å®ŀåľ¨æĺ¯å¤ª
    0.18
    ensive
    0.18
    olas
    0.18
    å®ŀåľ¨å¤ª
    0.17
    _stderr
    0.17
    Activations Density 0.125%

    No Known Activations