© 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. 62056
    Prev
    Next
    INDEX
    Explanations

    income eligibility, tax, security

    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
    gae
    -0.09
    ç°ĩ
    -0.09
    éģ¿å¼Ģ
    -0.09
    饱
    -0.08
    tod
    -0.08
    æĮ¯ãĤĬ
    -0.08
    夷
    -0.08
    ä½ĵ积
    -0.08
     Cle
    -0.08
    iagnostics
    -0.08
    POSITIVE LOGITS
    æĶ¶åħ¥
    0.16
     income
    0.14
    Income
    0.11
    income
    0.11
    è´¢åĬĽ
    0.11
     incomes
    0.10
    æĶ¶æĶ¯
    0.10
    _income
    0.10
     доÑħод
    0.10
    çŃīæĥħåĨµ
    0.10
    Activations Density 0.072%

    No Known Activations