© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 59017
    Prev
    Next
    INDEX
    Explanations

    Kauffman Stadium

    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
    ил
    -0.09
     Damian
    -0.09
    éķ¡
    -0.08
    åį´ä¸į
    -0.08
    ä¸ľæµ·
    -0.08
    尤为éĩįè¦ģ
    -0.08
    åķĨä¼ļ
    -0.08
    ActionResult
    -0.08
     hier
    -0.08
    UDA
    -0.08
    POSITIVE LOGITS
    çĭ¬
    0.10
    æĮł
    0.10
    ãĥ©ãĥ³ãĥī
    0.10
    åij»
    0.09
    çijĻ
    0.09
    å«Ĥ
    0.08
    ä¸ĭ鼨
    0.08
    æľīçļĦ
    0.08
    æį©
    0.08
    åīľ
    0.08
    Activations Density 0.038%

    No Known Activations