© 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. 36792
    Prev
    Next
    INDEX
    Explanations

    predicting future outcomes

    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
    éī´
    -0.10
    shal
    -0.09
    她说
    -0.08
    çģµæĦŁ
    -0.08
    interest
    -0.08
     sob
    -0.08
    _pan
    -0.08
    èµı
    -0.08
     society
    -0.08
    秩åºı
    -0.08
    POSITIVE LOGITS
    æīĵæ³ķ
    0.11
    åħļåĨħ
    0.11
    ç«ŀéĢī
    0.11
    篾
    0.10
    æĪĺæľ¯
    0.10
    飬
    0.10
    å¼±åĬ¿
    0.10
    æIJŃ
    0.10
    çŁŃæĿ¿
    0.10
    çŃĸçķ¥
    0.10
    Activations Density 0.230%

    No Known Activations