© 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. 29530
    Prev
    Next
    INDEX
    Explanations

    food, hunger, insecurity

    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
    Negative Logits
    /interface
    -0.09
     Abdullah
    -0.09
    swith
    -0.09
    ä½İä»·
    -0.09
    tractive
    -0.09
    寤
    -0.09
    åĩĿèģļåĬĽ
    -0.09
    errat
    -0.08
     Hers
    -0.08
    ä»Ģä¹Īéĥ½
    -0.08
    POSITIVE LOGITS
    èĻ¢
    0.10
    æīĢè°ĵçļĦ
    0.09
    Gear
    0.09
    纣
    0.09
    æĽ´å¤§çļĦ
    0.08
    æĹĹå¸ľ
    0.08
    merc
    0.08
    cker
    0.08
    æŃĩ
    0.08
    éļ¶å±ŀäºİ
    0.08
    Activations Density 0.011%

    No Known Activations