© 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. 13487
    Prev
    Next
    INDEX
    Explanations

    please send or contact

    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
    åħ¶å®ŀå°±æĺ¯
    -0.23
    æ¯ĽçĹħ
    -0.22
    åħ¶å¯¦
    -0.20
    åħ¶å®ŀ
    -0.20
    ENUM
    -0.18
    æĢ»ç®Ĺ
    -0.18
    èĢĮæĪIJ
    -0.18
    åĦ¿
    -0.18
    è¦ģä¸įè¦ģ
    -0.18
    .toInt
    -0.18
    POSITIVE LOGITS
    çĿģ
    0.23
    åħ³æ³¨
    0.23
    éģµå¾ª
    0.21
    èĩªè§ī
    0.21
    åħĪ
    0.21
    çķĻæĦı
    0.20
    妥åĸĦ
    0.20
    èĢĥèĻij
    0.20
    йÑĤеÑģÑĮ
    0.19
    åľ¨æİ¥åıĹ
    0.19
    Activations Density 0.014%

    No Known Activations