© 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. 24052
    Prev
    Next
    INDEX
    Explanations

    remaining quantities or items

    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
    heets
    -0.10
    廿
    -0.09
    rang
    -0.09
    rolls
    -0.09
    лиÑĨ
    -0.09
    lify
    -0.09
    º
    -0.08
    ä¿İ
    -0.08
    åı²ä¸Ĭ
    -0.08
    smith
    -0.08
    POSITIVE LOGITS
    许å¤ļ
    0.11
    most
    0.10
    ascus
    0.09
    åĩłç§į
    0.09
    /current
    0.09
    åĩłå®¶
    0.09
     beiden
    0.09
    æ±ģ
    0.09
    ampp
    0.08
    åĩłçĤ¹
    0.08
    Activations Density 0.009%

    No Known Activations