© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21180
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    åľ¨éĩĮéĿ¢
    -0.10
    æľ¬èº«
    -0.08
    OUCH
    -0.08
    åĩºåİ»
    -0.08
    éŃĤ
    -0.08
    ä¾£
    -0.08
    _periods
    -0.08
    cket
    -0.08
    åľ¨æľªæĿ¥
    -0.08
    åŃķ
    -0.08
    POSITIVE LOGITS
    éĿ¢åīį
    0.17
    èĦļä¸ĭ
    0.12
     karÅŁÄ±sında
    0.10
    éļħ
    0.10
    羣缸
    0.10
     Ø£ÙħاÙħ
    0.10
    好象
    0.09
    ä¹ĭä¸ĭ
    0.09
    çijŁ
    0.09
    å®Ľ
    0.09
    Activations Density 0.021%

    No Known Activations