© 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. 6069
    Prev
    Next
    INDEX
    Explanations

    prepositional phrases

    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
    Negative Logits
    ä¸į管æĺ¯
    -0.11
    ä¸į论æĺ¯
    -0.09
    åĪ°åºķæĺ¯
    -0.09
    çĶŁäº§çĶŁæ´»
    -0.09
    åįģåŃĹ
    -0.09
    å¿ĺè®°äºĨ
    -0.08
    æīĵæĭĽåij¼
    -0.08
    çľĭä¸Ģä¸ĭ
    -0.08
    inspace
    -0.08
    ä¹łæĥ¯äºĨ
    -0.08
    POSITIVE LOGITS
    rush
    0.10
    annon
    0.09
    egen
    0.08
    ẩ
    0.08
    åIJ¦
    0.08
    侬
    0.08
    bate
    0.08
    Fore
    0.08
    isle
    0.08
    erg
    0.08
    Activations Density 0.024%

    No Known Activations