© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 23996
    Prev
    Next
    INDEX
    Explanations

    money management

    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
    åıĮè¾¹
    -0.10
    ạt
    -0.09
     Beaut
    -0.09
     اÙĦصÙģ
    -0.09
    æ·ĸ
    -0.08
    èģĶåIJĪä¼ļ
    -0.08
    åľ°å¤Ħ
    -0.08
     поÑģÑĤоÑı
    -0.08
    éĢĢ
    -0.08
    ansk
    -0.08
    POSITIVE LOGITS
    çIJĨè´¢
    0.20
    è´¢åĬ¡
    0.15
    è´¢å¯Į
    0.13
    çļĦéĴ±
    0.12
    éĩijéĴ±
    0.12
    è´¢åĬ¡ç®¡çIJĨ
    0.12
     Financial
    0.12
    è´¢
    0.12
    èĩ´å¯Į
    0.12
    éĴ±å¸ģ
    0.12
    Activations Density 0.109%

    No Known Activations