© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 35941
    Prev
    Next
    INDEX
    Explanations

    decade ago or later

    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
    down
    -0.09
    untime
    -0.09
    меÑĢ
    -0.09
    datepicker
    -0.09
    ä»Ģä¹Īåij¢
    -0.09
    ducted
    -0.08
    çĿ¬
    -0.08
    ç»ıå¼Ģ
    -0.08
    å¥
    -0.08
    defs
    -0.08
    POSITIVE LOGITS
    ä¹ĭä½ľ
    0.13
    çĽ¸ä¼ł
    0.11
    -long
    0.11
    åĨħçļĦ
    0.10
    że
    0.09
    à¹īà¸Ļ
    0.09
    ëĿ½
    0.09
    æ¯Ļ
    0.09
    ones
    0.09
    å·²ä¹ħ
    0.09
    Activations Density 0.015%

    No Known Activations