© 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. 15083
    Prev
    Next
    INDEX
    Explanations

    WITHOUT ANY WARRANTY

    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
     zwar
    -0.32
    èĻ½çĦ¶
    -0.23
    æľ¬æĿ¥
    -0.21
    è¦ģä¹Ī
    -0.20
     thus
    -0.20
    åĽºçĦ¶
    -0.20
    çĦ¶èĢĮ
    -0.20
    éĽĸçĦ¶
    -0.19
     although
    -0.19
     Though
    -0.19
    POSITIVE LOGITS
    åIJĮæĹ¶ä¹Ł
    0.31
    ä¹Łæľī
    0.31
     nonetheless
    0.30
     nevertheless
    0.29
    åį´æĺ¯
    0.26
    ä¾ĿçĦ¶
    0.26
     ÑĤакже
    0.24
    ä¹Łæľīä¸ĢäºĽ
    0.24
    åį»
    0.24
     also
    0.23
    Activations Density 0.373%

    No Known Activations