© 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. 15979
    Prev
    Next
    INDEX
    Explanations

    must not, must retain

    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
     marque
    -0.18
    ä¸ĩä¸Ģ
    -0.18
    omat
    -0.18
    满满çļĦ
    -0.18
    大æ¦Ĥæĺ¯
    -0.17
    çī¹åĪ«æĺ¯
    -0.17
    家ä¼Ļ
    -0.16
    æĢ»è§īå¾Ĺ
    -0.16
    è°į
    -0.16
    åĵªæĢķ
    -0.16
    POSITIVE LOGITS
    /w
    0.31
    -have
    0.29
     бÑĭÑĤÑĮ
    0.26
    çĦ¶æĺ¯
    0.25
     be
    0.23
    s
    0.21
    lah
    0.21
    -être
    0.21
    /c
    0.20
    ä¹Łåıªèĥ½
    0.20
    Activations Density 0.037%

    No Known Activations