© 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. 29546
    Prev
    Next
    INDEX
    Explanations

    getting into or onto something

    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
    venir
    -0.10
     Vance
    -0.09
    ziel
    -0.09
    éĩijåŃĹ
    -0.09
    ificant
    -0.09
    паÑģ
    -0.09
    æ¥ļ
    -0.08
    lien
    -0.08
    åī§ç»Ħ
    -0.08
     sáng
    -0.08
    POSITIVE LOGITS
    åŁł
    0.09
    æľĪ以æĿ¥
    0.09
    第ä¸ī代
    0.09
    ä»Ģä¹Īä¸ľè¥¿
    0.09
     things
    0.09
    å¼Ģæĭĵ
    0.08
    社ä¼ļç§ijåѦ
    0.08
    çļĦä¸ľè¥¿
    0.08
    æѤäºĭ
    0.08
    ç¼Ł
    0.08
    Activations Density 0.021%

    No Known Activations