© 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. 16889
    Prev
    Next
    INDEX
    Explanations

    calls to action (please, buy, get, listen)

    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
     поÑĤомÑĥ
    -0.20
    åĽłä¸º
    -0.20
    ViewItem
    -0.19
    å°±ä¸įèĥ½
    -0.18
    ikut
    -0.18
    è·ijäºĨ
    -0.18
     اÙĦÙħص
    -0.18
     à¹Ģà¸ŀราะ
    -0.18
    èĺ§
    -0.17
    åĪĻ
    -0.17
    POSITIVE LOGITS
    åľ¨è¿Ļæĸ¹éĿ¢
    0.20
    åıĹ
    0.19
    ervo
    0.18
     accordingly
    0.18
    locked
    0.18
    iteDatabase
    0.18
    artz
    0.17
    _SIGNAL
    0.17
     relaxed
    0.17
     Accordingly
    0.17
    Activations Density 0.025%

    No Known Activations