© 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. 8288
    Prev
    Next
    INDEX
    Explanations

    weather and related suffixes

    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
    殿ä¸ĭ
    -0.11
    è¹Ī
    -0.10
    åĸĨ
    -0.09
    ä¸ĩæĪ·
    -0.09
    çļĦä¿¡ä»»
    -0.09
    ä¸ĬçıŃ
    -0.09
    人人éĥ½
    -0.09
    resh
    -0.08
    éĴ¦
    -0.08
    iros
    -0.08
    POSITIVE LOGITS
    hlen
    0.09
    OSE
    0.08
    ä»Ģä¹Īæł·
    0.08
    èĭŁ
    0.08
     Äijâu
    0.08
    edImage
    0.08
    ings
    0.08
    thew
    0.08
     slick
    0.08
     elementType
    0.08
    Activations Density 0.046%

    No Known Activations