© 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. 7029
    Prev
    Next
    INDEX
    Explanations

    sdk

    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
    çľĭçĤ¹
    -0.09
    ycop
    -0.08
    à¹ģà¸Ĺ
    -0.08
     EPS
    -0.08
    设置äºĨ
    -0.08
    .digital
    -0.08
    êm
    -0.08
    æľºåĬ¨
    -0.07
    prob
    -0.07
    refs
    -0.07
    POSITIVE LOGITS
    å¼Ģåıij
    0.15
    éĸĭçĻ¼
    0.12
    å¼ĢåıijèĢħ
    0.12
    _sdk
    0.10
    .sdk
    0.10
    客æĪ·çļĦ
    0.10
    èĩªå®¶
    0.10
    /sdk
    0.10
    åħ¥é©»
    0.10
    å¼Ģåıij建设
    0.10
    Activations Density 0.160%

    No Known Activations