© 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. 59436
    Prev
    Next
    INDEX
    Explanations

    locations often preceded by "in"

    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¸Ńä¿Ħ
    -0.10
     Nicar
    -0.10
     INDIRECT
    -0.09
     Rw
    -0.09
     Finnish
    -0.09
     Icelandic
    -0.09
     Americas
    -0.09
     Ethiopian
    -0.09
     Hungarian
    -0.08
    iras
    -0.08
    POSITIVE LOGITS
    éĤ£è¾¹
    0.10
    æ¡ĥ
    0.10
    缸éĤ»
    0.09
    è¿Ļä¸ªåľ°æĸ¹
    0.09
    ä¹ĭå¤ĸ
    0.08
    åİ¿åŁİ
    0.08
    éģ¥æݧ
    0.08
    çŃīåľ°
    0.08
    Disposition
    0.08
    åľ°åĮº
    0.08
    Activations Density 0.455%

    No Known Activations