© 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. 10346
    Prev
    Next
    INDEX
    Explanations

    parsley, Pars, pars, prairie parsley

    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
    ä¸Ĭ课
    -0.11
    สาร
    -0.10
    éºĴ
    -0.10
    佬
    -0.10
    稷
    -0.10
    èµ
    -0.09
    é»į
    -0.09
    éĵ¢
    -0.09
    coder
    -0.09
    że
    -0.09
    POSITIVE LOGITS
    áĢĦ
    0.10
    uste
    0.09
    à¹Ī
    0.09
    burgh
    0.08
    REA
    0.08
    åĨį说
    0.08
    Ñħод
    0.08
    rou
    0.08
     пÑĢог
    0.08
     jul
    0.08
    Activations Density 0.002%

    No Known Activations