© 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. 31095
    Prev
    Next
    INDEX
    Explanations

    mafia organizations and crime families

    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
    زاÙĦ
    -0.09
    à¹Ģà¸Ńà¸ĩ
    -0.08
    limited
    -0.08
    ival
    -0.08
    éģĵçIJĨ
    -0.08
    åºĩ
    -0.08
    èµļ
    -0.08
    åĩĿèģļåĬĽ
    -0.08
    åĮ®ä¹ı
    -0.08
    Åij
    -0.08
    POSITIVE LOGITS
    jong
    0.10
    orical
    0.10
    oru
    0.10
    arious
    0.09
     Torch
    0.09
    è¿Ļ对äºİ
    0.09
     dục
    0.09
    pollo
    0.09
    çĻ½èıľ
    0.09
    ieren
    0.08
    Activations Density 0.003%

    No Known Activations