© 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. 36656
    Prev
    Next
    INDEX
    Explanations

    Wh words

    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
    -0.11
    éļ³
    -0.09
    ture
    -0.09
    iven
    -0.09
    ../
    -0.09
    س
    -0.09
    omain
    -0.08
    ional
    -0.08
    .Arguments
    -0.08
    ger
    -0.08
    POSITIVE LOGITS
    åĭĥåĭĥ
    0.13
    soever
    0.13
    kus
    0.11
    -ever
    0.10
    é¢ı
    0.10
    çĦ¶æĺ¯
    0.10
    ÑĤек
    0.10
    å¨ĺ
    0.09
    atsapp
    0.09
    дÑĥм
    0.09
    Activations Density 0.030%

    No Known Activations