© 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. 12443
    Prev
    Next
    INDEX
    Explanations

    laws, bans, and statutes

    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
    å¼Ħ
    -0.23
    对åħ¶çľŁå®ŀ
    -0.21
    виÑĤ
    -0.20
    æĪ·åı£
    -0.19
    ä¸ĭä¸Ģ代
    -0.19
     ÑĤекÑĥÑī
    -0.18
     знак
    -0.18
    á»·
    -0.18
     Gerry
    -0.18
    line
    -0.18
    POSITIVE LOGITS
    æĺİç¡®è§Ħå®ļ
    0.27
    æĿ¡ä¾ĭ
    0.25
     поÑģколÑĮ
    0.24
    çĶŁæķĪ
    0.24
    ä¿ĿæĬ¤
    0.24
    æ³ķæ¡Ī
    0.23
     provisions
    0.23
     enacted
    0.23
    ÑĩÑĢежден
    0.23
    åİļåİļçļĦ
    0.23
    Activations Density 0.057%

    No Known Activations