© 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. 12195
    Prev
    Next
    INDEX
    Explanations

    son to die

    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
    lse
    -0.10
    大çģ«
    -0.08
     Abbey
    -0.08
     vign
    -0.08
    orts
    -0.08
    ä¸ĢæĬĬ
    -0.08
    æĮ¥
    -0.08
    åī¯ä¸»ä»»
    -0.08
    thy
    -0.08
    大æĪĺ
    -0.08
    POSITIVE LOGITS
    ement
    0.09
    .Criteria
    0.09
    æĦį
    0.08
    ç¬
    0.08
    æļĹ
    0.08
    çIJĨæĢ§
    0.08
    解说
    0.08
    è°Į
    0.08
    anth
    0.08
    _ie
    0.08
    Activations Density 0.015%

    No Known Activations