© 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. 13463
    Prev
    Next
    INDEX
    Explanations

    but that doesn't mean

    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
    çĶ¨èĩªå·±çļĦ
    -0.19
    å°¾
    -0.19
    ä»Ģä¹Īåľ°æĸ¹
    -0.19
     tail
    -0.18
    æ¼Ķ
    -0.18
    å¾Īéļ¾
    -0.18
    éĥ½æľīèĩªå·±
    -0.18
    æł¸å®ŀ
    -0.18
    èĮ«èĮ«
    -0.18
     drafts
    -0.17
    POSITIVE LOGITS
    ä¸įå½±åĵį
    0.24
    orman
    0.20
    hower
    0.19
    亲è¿ij
    0.19
    Still
    0.19
    oze
    0.18
    oven
    0.18
    并ä¸į代表
    0.18
     still
    0.18
    obili
    0.18
    Activations Density 0.026%

    No Known Activations