© 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. 947
    Prev
    Next
    INDEX
    Explanations

    heat waves and transfer

    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
    Not in Any Lists

    No Comments

    Negative Logits
    naire
    -0.10
    ambi
    -0.10
    hom
    -0.09
    è¦ģçŁ¥éģĵ
    -0.09
    骧
    -0.09
    erate
    -0.08
    UDGE
    -0.08
    xia
    -0.08
    åħ¥ä½ı
    -0.08
    hus
    -0.08
    POSITIVE LOGITS
    waves
    0.11
    忱
    0.10
    è¡·
    0.10
    flix
    0.09
    ening
    0.09
    lessness
    0.09
    lify
    0.09
    fully
    0.09
    ronym
    0.09
    stroke
    0.09
    Activations Density 0.036%

    No Known Activations