© 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. 11533
    Prev
    Next
    INDEX
    Explanations

    Department of

    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
    ä½ľä¸ºä¸ĢåIJį
    -0.19
    ä¸Ģ代
    -0.18
    ERP
    -0.18
     chances
    -0.18
    hare
    -0.17
    èĪ¬
    -0.17
    ä¸Ģå¹ħ
    -0.17
     kadar
    -0.17
    çĸij
    -0.17
    ro
    -0.17
    POSITIVE LOGITS
    æķĻèĤ²åŁ¹è®Ń
    0.19
    å¢ŀåĬłåĢ¼
    0.19
    æıIJä¾Ľä¼ĺè´¨
    0.19
    ﹩
    0.19
    ç»
    0.19
    çŃīéĥ¨éŨ
    0.18
    éħ©
    0.18
    ahoma
    0.18
    顽
    0.18
    åģļçļĦäºĭæĥħ
    0.18
    Activations Density 0.009%

    No Known Activations