© 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. 26223
    Prev
    Next
    INDEX
    Explanations

    uk based defense contractor

    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
    дей
    -0.09
    STONE
    -0.09
    æĬ¼éĩij
    -0.09
    olan
    -0.09
    iesen
    -0.08
     обÑĭ
    -0.08
    åIJ¬è¿ĩ
    -0.08
    _frm
    -0.08
     Nug
    -0.08
    CHANNEL
    -0.08
    POSITIVE LOGITS
    åĽ½éĺ²
    0.11
    éĶ»
    0.10
    åĶ®åIJİæľįåĬ¡
    0.10
    çłĶåĪ¶
    0.10
    æĶ¹è£ħ
    0.10
    æ°ijéĸĵ
    0.10
    客æĪ·éľĢæ±Ĥ
    0.09
    èĥ´
    0.09
    åĪ¶éĢł
    0.09
    æľªç»ı
    0.09
    Activations Density 0.059%

    No Known Activations