© 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. 47492
    Prev
    Next
    INDEX
    Explanations

    Gold related surnames

    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
    éĻ¬
    -0.10
    ../../../
    -0.10
    ened
    -0.09
    å¾Ĵ
    -0.09
    оÑģÑĤи
    -0.09
    ogens
    -0.08
    ptune
    -0.08
    atics
    -0.08
    icular
    -0.08
    ðŁı»
    -0.08
    POSITIVE LOGITS
    à¹ģà¸Ķà¸ĩ
    0.10
    çĻ½éĵ¶
    0.10
    даÑĢ
    0.09
    ç®Ķ
    0.09
    åĮ®
    0.09
     Sachs
    0.09
    à¸Ħำ
    0.09
    owing
    0.09
    ë¹Ľ
    0.08
    arily
    0.08
    Activations Density 0.132%

    No Known Activations