© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 56302
    Prev
    Next
    INDEX
    Explanations

    meaning different things

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    adamkarvonen/qwen3-32b-saes/saes_Qwen_Qwen3-32B_batch_top_k/resid_post_layer_32
    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
    èµ°
    -0.09
     ÑĢеб
    -0.09
    åı¯è§ģ
    -0.08
    离å¼ĢäºĨ
    -0.08
     ups
    -0.08
    éĩ
    -0.08
    illard
    -0.07
    èįĴ
    -0.07
    _globals
    -0.07
    éĻĨ
    -0.07
    POSITIVE LOGITS
    æĦıåij³çĿĢ
    0.22
    åIJ«ä¹ī
    0.22
    çļĦæĦıæĢĿ
    0.21
    æĦıæĢĿ
    0.19
     meaning
    0.18
    è¿ĻæĦıåij³çĿĢ
    0.18
    æĦıæĢĿæĺ¯
    0.17
     meanings
    0.17
     nghĩa
    0.16
    çļĦæĦıä¹ī
    0.16
    Activations Density 0.231%

    No Known Activations