© 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. 39676
    Prev
    Next
    INDEX
    Explanations

    articles followed by specific terms

    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
    åŃ£åº¦
    -0.11
    éĥ½ä¸įä¼ļ
    -0.09
    é»ı
    -0.09
    çĿ¦
    -0.09
    ä¸ĢéĿ¢
    -0.09
     (!((
    -0.08
    IPP
    -0.08
    å±IJ
    -0.08
    辩è¯ģ
    -0.08
     Sole
    -0.08
    POSITIVE LOGITS
    ç»
    0.11
    onta
    0.09
    بارÙĥ
    0.09
    æij¸
    0.09
    é¹ĥ
    0.08
    antha
    0.08
     Desire
    0.08
    ogh
    0.08
     ç§
    0.08
     Hen
    0.08
    Activations Density 0.530%

    No Known Activations