© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 5713
    Prev
    Next
    INDEX
    Explanations

    definition of "first"

    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
    bps
    -0.09
    pent
    -0.09
    hex
    -0.09
    é¦Ĵ头
    -0.09
    è±ĨèħIJ
    -0.09
    STRU
    -0.09
    sons
    -0.08
    oldt
    -0.08
    驹
    -0.08
    agne
    -0.08
    POSITIVE LOGITS
    xed
    0.10
    :///
    0.09
     rid
    0.08
    ederation
    0.08
    æ¼Ĥæµģ
    0.08
    InBackground
    0.08
    auc
    0.08
    .ld
    0.08
    <Field
    0.08
    çĩ¥
    0.08
    Activations Density 0.020%

    No Known Activations