© 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. 12419
    Prev
    Next
    INDEX
    Explanations

    Abbey, Ab, abbr

    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
    flake
    -0.10
     Dixon
    -0.09
    umber
    -0.09
     Tus
    -0.09
    erness
    -0.09
    iest
    -0.09
    istics
    -0.09
    âľª
    -0.08
    orous
    -0.08
    yer
    -0.08
    POSITIVE LOGITS
    -minded
    0.12
    OLUTE
    0.12
    andoned
    0.11
    raries
    0.11
    olutely
    0.10
    alom
    0.10
    çĦ¶æĺ¯
    0.10
    bies
    0.10
    stract
    0.10
    ively
    0.09
    Activations Density 0.081%

    No Known Activations