© 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. 12436
    Prev
    Next
    INDEX
    Explanations

    educational institutions and fields of study

    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
    åľ£
    -0.10
    èĽŁ
    -0.10
    纹
    -0.09
     Morse
    -0.09
    ingu
    -0.09
    æĦıåIJij
    -0.09
    ingo
    -0.09
    бо
    -0.09
    uyo
    -0.09
    URY
    -0.08
    POSITIVE LOGITS
    ãģ¤ãģį
    0.09
    utom
    0.09
    akis
    0.09
    è¡Įä¸ļçļĦ
    0.09
    æĻ°
    0.08
    大åѦæ¯ķä¸ļ
    0.08
     Planned
    0.08
    éªĹåıĸ
    0.08
    鸡èĤī
    0.08
    ignite
    0.08
    Activations Density 0.079%

    No Known Activations