© 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. 60832
    Prev
    Next
    INDEX
    Explanations

    Pfaffenbauer

    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
    fung
    -0.11
    fuse
    -0.10
    fld
    -0.10
    ality
    -0.10
    frequency
    -0.10
    Ùģس
    -0.10
    ford
    -0.10
    аÑĪ
    -0.09
    aise
    -0.09
    fav
    -0.09
    POSITIVE LOGITS
    rence
    0.17
    uentes
    0.16
    aisal
    0.14
    razier
    0.13
    icial
    0.13
    icient
    0.13
    irma
    0.13
    inition
    0.13
    letcher
    0.13
    initely
    0.13
    Activations Density 0.800%

    No Known Activations