© 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. 37025
    Prev
    Next
    INDEX
    Explanations

    steep terrain or slopes

    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
    naire
    -0.10
    -important
    -0.09
    omes
    -0.08
    mos
    -0.08
     Ying
    -0.08
    못
    -0.08
    aina
    -0.08
    好åĿı
    -0.08
    ifle
    -0.08
     Bowling
    -0.08
    POSITIVE LOGITS
    ening
    0.13
    -sided
    0.12
    pling
    0.11
    emente
    0.11
    ened
    0.11
    ly
    0.11
     جدا
    0.10
    side
    0.10
    èµ°ä¸ĭåİ»
    0.10
    edor
    0.09
    Activations Density 0.003%

    No Known Activations