© 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. 15039
    Prev
    Next
    INDEX
    Explanations

    not only

    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
    æĸ°åĨľæĿij
    -0.20
    å¾Īæľī
    -0.19
    çļĦ缮åħī
    -0.18
    æ£ĺ
    -0.18
    Unsigned
    -0.18
     педаг
    -0.18
    eldon
    -0.18
    æĻ®éģįåŃĺåľ¨
    -0.18
    ä»Ģä¹Īä¸ľè¥¿
    -0.18
     Misc
    -0.18
    POSITIVE LOGITS
    ä¸įä»ħæĺ¯
    0.22
    ä¸įä»ħ
    0.21
    ä½Ĩä¸įéĻIJäºİ
    0.21
     only
    0.21
    ä¸įä»ħä»ħæĺ¯
    0.20
     ÑĤолÑĮко
    0.20
    ä¸įéĻIJ
    0.20
    ãģłãģijãģ§ãģªãģı
    0.19
    å°¤åħ¶æĺ¯
    0.19
    undi
    0.19
    Activations Density 0.028%

    No Known Activations