© 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. 8623
    Prev
    Next
    INDEX
    Explanations

    sports tournament teams

    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
     raft
    -0.09
    è°Ľ
    -0.09
    åĪĨ红
    -0.09
    天涯
    -0.09
    _opts
    -0.09
    çĪ¶äº²
    -0.09
    æĮij
    -0.09
    åĮĢ
    -0.09
    å«Ĥ
    -0.09
    读åIJİ
    -0.09
    POSITIVE LOGITS
    纵
    0.09
     Masc
    0.09
    æīĽ
    0.09
    filesystem
    0.09
    åŁİå¸Ĥ管çIJĨ
    0.08
    éĻ¶
    0.08
    åĪ¶å®ļäºĨ
    0.08
    åŁİ
    0.08
    URN
    0.08
    縱
    0.08
    Activations Density 0.129%

    No Known Activations