© 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. 26042
    Prev
    Next
    INDEX
    Explanations

    "blow" or "punch"

    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
    æĭĺ
    -0.11
    æµij
    -0.10
    èĵģ
    -0.10
    æĻ¤
    -0.10
    èij±
    -0.09
    .synthetic
    -0.09
     redeem
    -0.09
    å³¥
    -0.09
    éļĺ
    -0.09
    è¶Ĭé«ĺ
    -0.08
    POSITIVE LOGITS
    èĩ´åij½
    0.15
     blows
    0.14
     blow
    0.13
    æīĵåĩ»
    0.12
    éĴĪ
    0.12
    ä¸ĢåĪĢ
    0.11
     punch
    0.11
     Blow
    0.11
    åĩ»
    0.10
    éĩĿ
    0.10
    Activations Density 0.061%

    No Known Activations