© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 9856
    Prev
    Next
    INDEX
    Explanations

    payment, money, salary, compensation

    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
    åħľ
    -0.11
    éĻįä»·
    -0.10
    éĻį
    -0.09
    éĤ£ä¹Īç®Ģåįķ
    -0.09
    龸éģĵ
    -0.08
     pus
    -0.08
    æĶ¶è´¹
    -0.08
    gain
    -0.08
    pond
    -0.08
    rint
    -0.08
    POSITIVE LOGITS
    .Tables
    0.09
    åħ¼èģĮ
    0.09
    arel
    0.09
    aryl
    0.09
    åī¯
    0.08
    å®ģ
    0.08
    abal
    0.08
    å¸Ľ
    0.08
    åįĥåı¤
    0.08
     Че
    0.08
    Activations Density 0.055%

    No Known Activations