© 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. 12620
    Prev
    Next
    INDEX
    Explanations

    buying online

    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
    æ½ľ
    -0.23
    çĶŁå§ľ
    -0.18
    çıĬçijļ
    -0.18
    çIJ®
    -0.17
    .ep
    -0.17
     Giles
    -0.17
    æ¿ĢåĬ±
    -0.17
     tentative
    -0.17
    	stop
    -0.17
     поÑģл
    -0.17
    POSITIVE LOGITS
    wards
    0.20
    ially
    0.19
    ä¸įçķĻ
    0.18
    _bulk
    0.18
    à¹ģà¸ļà¸ļ
    0.17
    British
    0.17
    ifr
    0.17
    åıijå±ķ空éĹ´
    0.17
    ally
    0.17
    elves
    0.17
    Activations Density 0.027%

    No Known Activations