© 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. 55122
    Prev
    Next
    INDEX
    Explanations

    positive emotion

    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
    åİ»åĵªåĦ¿
    -0.10
    çļĦéŃħåĬĽ
    -0.10
    ä¹ı
    -0.09
    èį·
    -0.08
     attract
    -0.08
    ä¸ĸ
    -0.08
    inus
    -0.08
    gard
    -0.08
    ç¥Ŀè´º
    -0.08
    uar
    -0.08
    POSITIVE LOGITS
    欣æħ°
    0.10
    èµį
    0.10
    èĢģ人
    0.09
    èı½
    0.09
    èİŀ
    0.09
    æĩĤäºĭ
    0.09
    ä¾Ķ
    0.09
    èıĢ
    0.09
    èİ«è¿ĩäºİ
    0.09
    ãĥ¡ãĥ¼ãĤ
    0.09
    Activations Density 0.034%

    No Known Activations