© 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. 6076
    Prev
    Next
    INDEX
    Explanations

    Murray

    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
    çĦ¶æĺ¯
    -0.14
    ë¥ł
    -0.12
    ãģĤãģ¾ãĤĬ
    -0.11
    ëģĶ
    -0.10
    egers
    -0.10
    æĢ§å¼º
    -0.10
    ãĥ¥
    -0.10
    ï¸
    -0.10
    imal
    -0.09
    Ùij
    -0.09
    POSITIVE LOGITS
    ank
    0.10
    åĬŀäºĭå¤Ħ
    0.10
    inson
    0.09
    halb
    0.09
    utom
    0.09
    edImage
    0.09
     kiá»ĩn
    0.09
    çķĶ
    0.09
    INGS
    0.08
    /is
    0.08
    Activations Density 0.015%

    No Known Activations