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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 52351
    Prev
    Next
    INDEX
    Explanations

    budget, income, poverty, luxury, precision

    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
    ispers
    -0.09
    åIJ»
    -0.09
    Cas
    -0.08
    å¹´åĪĿ
    -0.08
    çĪ°
    -0.08
    èĦĬ
    -0.08
    æĬ¬
    -0.08
     Kiss
    -0.08
     Intern
    -0.08
    âļª
    -0.08
    POSITIVE LOGITS
    _seqs
    0.09
    emy
    0.09
    çģ«çĤ¬
    0.09
    åĶ¯æľī
    0.09
    ä¸ĵèģĮ
    0.09
     GiriÅŁ
    0.09
    å¤ķéĺ³
    0.09
     MCC
    0.09
    astic
    0.08
    ative
    0.08
    Activations Density 0.072%

    No Known Activations