© 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. 58545
    Prev
    Next
    INDEX
    Explanations

    past time references

    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
    è´¯éĢļ
    -0.10
    ç²ī
    -0.10
    åĬŀäºĭ
    -0.09
    说ä»Ģä¹Ī
    -0.09
    idata
    -0.09
    .exchange
    -0.08
    çģµæķı
    -0.08
    çįł
    -0.08
    _endian
    -0.08
    æ¹Ľ
    -0.08
    POSITIVE LOGITS
    åŁĥåıĬ
    0.12
    é§IJ
    0.11
     Egypt
    0.11
     Egyptian
    0.10
    èĭ¦
    0.10
    Egypt
    0.10
    é©»
    0.09
    èIJ¥åľ°
    0.09
    éķ¿å¾ģ
    0.09
    çļĦåİĨåı²
    0.09
    Activations Density 0.033%

    No Known Activations