© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50904
    Prev
    Next
    INDEX
    Explanations

    aircraft crash

    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
    æ³³
    -0.10
    å®Ī
    -0.10
    å»
    -0.10
    å¥ĩå¦Ļ
    -0.09
    éĤĥ
    -0.09
     обÑıз
    -0.09
    å¼Ģ设
    -0.09
    åİ©
    -0.09
    geois
    -0.09
    dbl
    -0.09
    POSITIVE LOGITS
    å½ĵæŶ
    0.10
    åĿł
    0.10
    site
    0.09
     fatal
    0.09
    丰满
    0.08
    èIJ½ãģ¡
    0.08
    åľ¨æĦı
    0.08
    æ²¥
    0.08
    èĩ
    0.08
     Fuller
    0.08
    Activations Density 0.039%

    No Known Activations