© 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. 60681
    Prev
    Next
    INDEX
    Explanations

    prevent slippage and movement

    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
    ç½²
    -0.11
    èĹī
    -0.10
    èľĩ
    -0.10
    iox
    -0.09
     жив
    -0.09
    wolf
    -0.09
    ENTS
    -0.09
    åĥµå°¸
    -0.09
    argar
    -0.09
    å±ħ室
    -0.09
    POSITIVE LOGITS
    èĦ±èIJ½
    0.10
    æµģ失
    0.09
     loose
    0.09
     Kemp
    0.09
    èĪ«
    0.09
     loosen
    0.08
    æĿ¾
    0.08
     during
    0.08
    è°·
    0.08
    å¿Ļ
    0.08
    Activations Density 0.115%

    No Known Activations