© 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. 15591
    Prev
    Next
    INDEX
    Explanations

    staying in mind

    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
    顺便
    -0.25
    èĶ·
    -0.21
    æł¹æľ¬ä¸į
    -0.19
    anos
    -0.19
    inine
    -0.19
    åŁİå¸Ĥ群
    -0.19
    æł¹æľ¬å°±ä¸į
    -0.19
    è°¤
    -0.19
    edBy
    -0.19
    åı±
    -0.19
    POSITIVE LOGITS
    ä½Ļ
    0.22
    è¿Ļåĩłå¤©
    0.21
     HOL
    0.21
    èĦijæµ·
    0.19
    _TAGS
    0.19
    æµ®
    0.19
    æĻĥ
    0.19
    æŶæŶ
    0.18
    æľĢè¿ij
    0.18
    éĤ£æ®µ
    0.18
    Activations Density 0.021%

    No Known Activations