© 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. 26300
    Prev
    Next
    INDEX
    Explanations

    Oracle and

    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
    olk
    -0.10
    nah
    -0.09
    çĦ¶æĺ¯
    -0.09
    rière
    -0.09
    dag
    -0.09
    åħĴ
    -0.08
    åĦ¿
    -0.08
    andard
    -0.08
    elier
    -0.08
    è¾ij
    -0.08
    POSITIVE LOGITS
    ving
    0.11
    碼
    0.10
    ../
    0.09
    cling
    0.09
    æľŁæľ«
    0.09
     Arabia
    0.09
    ife
    0.09
    itÃł
    0.09
    ç¤ģ
    0.09
    ع
    0.09
    Activations Density 0.016%

    No Known Activations