© 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. 8686
    Prev
    Next
    INDEX
    Explanations

    heart attack

    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
    æĸ©
    -0.11
    ãģĮãģĭãģĭ
    -0.09
    æ´İ
    -0.09
    æĥ©
    -0.09
    annon
    -0.09
    ç¼°
    -0.08
    åIJĬ
    -0.08
    rhs
    -0.08
    ãĤįãģĨ
    -0.08
    诱人
    -0.08
    POSITIVE LOGITS
    åıijä½ľ
    0.12
    çªģåıij
    0.11
    åħ¬å¼Ģåıij
    0.10
    ç¿»
    0.10
    äºĨä¸Ģåľº
    0.09
    ä¸į失
    0.09
    å²
    0.09
    主页
    0.09
    è¿Ļç¯ĩæĸĩç«ł
    0.09
    IRT
    0.09
    Activations Density 0.105%

    No Known Activations