© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 50899
    Prev
    Next
    INDEX
    Explanations

    style and sophistication

    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
    æ²Ļ滩
    -0.09
    åIJİæİĴ
    -0.09
     Anim
    -0.09
    æĥħåĨµæĿ¥çľĭ
    -0.09
    азв
    -0.09
    å¾Īå·®
    -0.08
    ãĤıãģij
    -0.08
     лиÑĤеÑĢаÑĤÑĥÑĢ
    -0.08
    ATORS
    -0.08
    assi
    -0.08
    POSITIVE LOGITS
    æ®·
    0.11
    ä¼ij
    0.10
    åįķåĵģ
    0.09
     domina
    0.08
    åį´åıĪ
    0.08
     sens
    0.08
    æľªå©ļ
    0.08
     nhẹ
    0.08
    éĤ£ä»½
    0.08
    åģ¶å°Ķ
    0.08
    Activations Density 0.079%

    No Known Activations