© 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. 59241
    Prev
    Next
    INDEX
    Explanations

    belt

    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
    ¤
    -0.10
    illion
    -0.10
    eses
    -0.09
    enic
    -0.09
    etal
    -0.09
    iddle
    -0.09
    ä¸įäºĨ
    -0.08
    eti
    -0.08
    ãģĹãģ¾ãģĦ
    -0.08
    esco
    -0.08
    POSITIVE LOGITS
    ties
    0.13
    ows
    0.11
    unes
    0.11
    ayed
    0.09
    BIND
    0.09
     buckle
    0.09
    ä¸Ĭæľī
    0.09
    åĨħçļĦ
    0.08
    èĩ¾
    0.08
    èĤļ
    0.08
    Activations Density 0.007%

    No Known Activations