© 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. 15763
    Prev
    Next
    INDEX
    Explanations

    preservative

    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
    UFF
    -0.21
    æݨ
    -0.20
    èĻļ
    -0.20
    ased
    -0.20
    uff
    -0.19
     manipulated
    -0.19
    æĶ¾ä¸ĭ
    -0.19
    _processor
    -0.18
    åľ°ä½į
    -0.18
    åĬŁçİĩ
    -0.18
    POSITIVE LOGITS
    éĺ²
    0.21
    æ¶Īæ¯Ĵ
    0.21
    odox
    0.21
    æĿĢèıĮ
    0.20
    çļĦå®īåħ¨
    0.20
    éĺ²çģ«
    0.20
    éĺ²æݧ
    0.19
    éĺ²æ²»
    0.19
    éĺ²èħIJ
    0.19
    éĺ²æĬ¤
    0.19
    Activations Density 0.015%

    No Known Activations