© 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. 26026
    Prev
    Next
    INDEX
    Explanations

    in to a place

    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
    åĪĹåħ¥
    -0.08
    éĸĵéģķãģĦ
    -0.08
    èIJ½åħ¥
    -0.08
    çĥ¤
    -0.08
    æĻļæľŁ
    -0.08
     transporte
    -0.08
    ç°ĭ
    -0.08
    Ñģим
    -0.08
    صب
    -0.08
    æ§
    -0.08
    POSITIVE LOGITS
    çľ¼éĩĮ
    0.10
    éĩįçĤ¹åħ³æ³¨
    0.09
    å®Įæķ´çļĦ
    0.09
    åĬ¡å¿ħ
    0.08
    PLIC
    0.08
    ç½®
    0.08
    éĢı
    0.08
    åŃº
    0.08
    éĩĬ
    0.08
    客æ°Ķ
    0.08
    Activations Density 0.020%

    No Known Activations