© 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. 22518
    Prev
    Next
    INDEX
    Explanations

    prefix "ext"

    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
    hips
    -0.09
    edList
    -0.09
    éļį
    -0.09
    rous
    -0.09
    seau
    -0.08
    éªŀ
    -0.08
    æİĮ声
    -0.08
    eer
    -0.08
     Florian
    -0.08
    hip
    -0.08
    POSITIVE LOGITS
    inction
    0.13
    reme
    0.12
    remely
    0.12
    inctions
    0.11
    ablish
    0.11
    ensively
    0.10
     бил
    0.10
    Rails
    0.10
    oring
    0.10
    åĪĨæĺİ
    0.10
    Activations Density 0.021%

    No Known Activations