© 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. 15262
    Prev
    Next
    INDEX
    Explanations

    tricky, problematic, dubious, slick

    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
    åĸĩåıŃ
    -0.20
     phẩm
    -0.18
    омеÑĢ
    -0.17
    izational
    -0.17
    esimal
    -0.17
    âĨĻ
    -0.17
    аниз
    -0.17
    è½¼
    -0.16
    anian
    -0.16
    acional
    -0.16
    POSITIVE LOGITS
    weise
    0.21
    æݪ
    0.20
     Situation
    0.19
    æ£ĺ
    0.19
     wording
    0.19
    åı°é£İ
    0.18
    -haired
    0.18
    æľīæĦıæĢĿçļĦ
    0.18
    ä¸įæ¸ħ
    0.18
    åı¯éĿłçļĦ
    0.17
    Activations Density 0.012%

    No Known Activations