© 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. 14963
    Prev
    Next
    INDEX
    Explanations

    US zip codes

    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
    æĻĸ
    -0.20
    ifes
    -0.20
    çļĦä¼Łå¤§
    -0.19
    åıĤ
    -0.18
    åĩ«
    -0.18
    ì¢Į
    -0.18
    çļĦéģĵçIJĨ
    -0.17
    _endian
    -0.17
    олж
    -0.17
    _second
    -0.17
    POSITIVE LOGITS
    ä¸Ĭ游
    0.21
    åģľä¸ĭæĿ¥
    0.20
    èģĶ绾
    0.20
    ADER
    0.20
    å´ĩ
    0.19
    ç¼®
    0.19
    åݿ级
    0.19
    æĥħåĨµè¿Ľè¡Į
    0.18
    æµĨ
    0.18
    áŀ¶áŀ
    0.18
    Activations Density 0.009%

    No Known Activations