© 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. 945
    Prev
    Next
    INDEX
    Explanations

    gu followed by morpheme

    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
    Not in Any Lists

    No Comments

    Negative Logits
    ding
    -0.10
    ETING
    -0.09
    ÑĦин
    -0.09
    ferred
    -0.09
    媳
    -0.09
    opr
    -0.09
     thiá»ĥu
    -0.09
    bia
    -0.08
    richt
    -0.08
    äºĨä¸Ģ个
    -0.08
    POSITIVE LOGITS
    illaume
    0.11
    ance
    0.10
    代表æĢ§
    0.10
    paces
    0.10
    ties
    0.09
    erry
    0.09
    ays
    0.09
    ards
    0.09
    ANCE
    0.09
    è°£
    0.09
    Activations Density 0.036%

    No Known Activations