© 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. 59358
    Prev
    Next
    INDEX
    Explanations

    State bred horses

    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
     Jord
    -0.09
    解说
    -0.08
    lements
    -0.08
    派驻
    -0.08
    æ¯ķ
    -0.08
    æĵį
    -0.08
    å¤ķ
    -0.08
     Cricket
    -0.08
     Penguin
    -0.07
     fid
    -0.07
    POSITIVE LOGITS
    饲
    0.12
    稳å®ļçļĦ
    0.11
    çŃĸ
    0.11
    åħ»æ®ĸæĪ·
    0.10
    åİ©
    0.10
    åħ»èĤ²
    0.10
    bred
    0.10
    åħ»æ®ĸ
    0.10
    éĢĢå½¹
    0.10
    稳
    0.09
    Activations Density 0.026%

    No Known Activations