© 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. 8516
    Prev
    Next
    INDEX
    Explanations

    nearly + quantifier

    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
    еÑĩение
    -0.09
    èĵĿ天
    -0.08
    ent
    -0.08
    éĽĴ
    -0.08
    gel
    -0.08
    avers
    -0.08
     mere
    -0.08
    éĢĶ
    -0.08
     множеÑģÑĤво
    -0.08
    æ¸Ŀ
    -0.08
    POSITIVE LOGITS
    mente
    0.14
     à¹Ĩ
    0.11
    íŀĪ
    0.10
    emente
    0.10
    theless
    0.10
    ê¹IJ
    0.10
    ãģĤãĤĭ
    0.10
    åħļæĢ»
    0.10
    à¹Ĩ
    0.10
    äºİæѤ
    0.09
    Activations Density 0.029%

    No Known Activations