© 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. 39071
    Prev
    Next
    INDEX
    Explanations

    opening quotation marks

    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
    åĩłå®¶
    -0.11
     há»ģ
    -0.09
    åģ¶
    -0.08
    诣
    -0.08
    æīĢæīĢ
    -0.08
     اÙĦÙĩÙĨد
    -0.08
     alan
    -0.08
    antha
    -0.07
    æĸ°çļĦä¸Ģ
    -0.07
    æŶåĢĻ
    -0.07
    POSITIVE LOGITS
    ibly
    0.10
    itters
    0.09
    URY
    0.08
    .Claims
    0.08
    esus
    0.08
    ELLOW
    0.08
    -fw
    0.08
    خذ
    0.08
    ules
    0.08
     возд
    0.08
    Activations Density 0.107%

    No Known Activations