© 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. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38355
    Prev
    Next
    INDEX
    Explanations

    place names with non-Latin characters

    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
    ä¸Ģä¸Ŀ
    -0.08
    ailable
    -0.08
     gast
    -0.08
    è¡ĮåĪĹ
    -0.08
    åĩ¼
    -0.08
    é£Ł
    -0.08
    çĻ»å±±
    -0.08
    é¥
    -0.08
     utility
    -0.07
     undisclosed
    -0.07
    POSITIVE LOGITS
    åı¤åŁİ
    0.15
    åı¤éķĩ
    0.14
    éģĹåĿĢ
    0.10
    éģĹçķĻ
    0.10
    rcode
    0.10
    æĤłä¹ħ
    0.10
    éĤĪ
    0.10
    ANO
    0.10
    _Native
    0.09
    _PD
    0.09
    Activations Density 0.099%

    No Known Activations