© 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. 6787
    Prev
    Next
    INDEX
    Explanations

    retirement savings accounts

    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
    ç¬ijèĦ¸
    -0.11
    åĴ±
    -0.10
    icorn
    -0.10
     Carey
    -0.09
    nl
    -0.09
    åıĪè¦ģ
    -0.09
    æİĪ
    -0.09
    æĹ¢è¦ģ
    -0.09
    çľĭä»ĸ
    -0.09
     parts
    -0.09
    POSITIVE LOGITS
    åħ»èĢģéĩij
    0.11
     Portable
    0.09
     portable
    0.09
     Nest
    0.09
    éĢĢä¼ij
    0.08
    IMENT
    0.08
     sr
    0.08
     retirement
    0.08
    å·¢
    0.08
    éªł
    0.08
    Activations Density 0.073%

    No Known Activations