© 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. 29414
    Prev
    Next
    INDEX
    Explanations

    scandal and its aftermath

    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
    ters
    -0.09
    ingle
    -0.09
    uters
    -0.09
    bon
    -0.09
    TING
    -0.08
    Ñģ
    -0.08
    iny
    -0.08
    ucha
    -0.08
    esty
    -0.08
     Сов
    -0.08
    POSITIVE LOGITS
    ous
    0.15
    ously
    0.11
    å·²ä¹ħ
    0.10
    åħ¶å®ĥéĹ®é¢ĺ
    0.10
    æĢ§çĸ¾çĹħ
    0.09
    éĥĹ
    0.09
    itous
    0.09
    izer
    0.09
    æĻ°
    0.09
    opol
    0.09
    Activations Density 0.003%

    No Known Activations