© 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. 36694
    Prev
    Next
    INDEX
    Explanations

    passion for something

    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
    ä¿ļ
    -0.10
    å¬Ĺ
    -0.09
    odon
    -0.09
    anko
    -0.09
    èľ»
    -0.08
    åıĸè¯ģ
    -0.08
    泯
    -0.08
     Hanna
    -0.08
    çıº
    -0.08
    .Exists
    -0.08
    POSITIVE LOGITS
    æ¿Ģæĥħ
    0.20
     passion
    0.19
     Passion
    0.16
    çĥŃæĥħ
    0.16
    çļĦçĥŃæĥħ
    0.14
     passionate
    0.14
     passions
    0.12
    çĥŃçĪ±
    0.11
    çĥŃè¡Ģ
    0.11
    çĥĪ
    0.11
    Activations Density 0.080%

    No Known Activations