© 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. 51986
    Prev
    Next
    INDEX
    Explanations

    Sir titles

    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
    elder
    -0.09
    idend
    -0.09
    ieber
    -0.08
    éĴĩ
    -0.08
    eko
    -0.08
    许åı¯è¯ģ
    -0.08
     Yun
    -0.08
    æĶ»åĬ¿
    -0.08
    enie
    -0.08
     same
    -0.08
    POSITIVE LOGITS
    å¾Ĺä½ı
    0.11
    alis
    0.10
    ships
    0.10
    ral
    0.09
    åĮĸè¿Ľç¨ĭ
    0.09
    owie
    0.09
    kest
    0.09
    thumb
    0.09
    akter
    0.09
    æŃª
    0.09
    Activations Density 0.014%

    No Known Activations