© 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. 59393
    Prev
    Next
    INDEX
    Explanations

    is/does/will questions

    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
    大æ¦Ĥ
    -0.10
    å¾·å°Ķ
    -0.10
    èĤ¯å®ļ
    -0.10
    æŁ°
    -0.10
    éĿŀ常å¤ļçļĦ
    -0.10
    âģĤ
    -0.10
     вн
    -0.09
    LING
    -0.09
    ãĥŃãĥ¼ãĥ³
    -0.09
    ооÑĢ
    -0.09
    POSITIVE LOGITS
    ulf
    0.10
    ecessarily
    0.09
    2
    0.08
    1
    0.08
    ix
    0.08
    3
    0.08
    vi
    0.08
    è¿Ļå°±æĺ¯
    0.08
    è¿ĺéľĢ
    0.08
     bl
    0.08
    Activations Density 0.113%

    No Known Activations