© 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. 50312
    Prev
    Next
    INDEX
    Explanations

    at home

    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
    åľ¨æѤä¹ĭåīį
    -0.10
    åĵij
    -0.09
     Taxi
    -0.09
    æł·çļĦ
    -0.09
    owy
    -0.09
    -0.09
    责任åĪ¶
    -0.08
    à¹Į
    -0.08
    oded
    -0.08
    æ°¸ä¹ħ
    -0.08
    POSITIVE LOGITS
    ulin
    0.09
    ense
    0.09
    诸侯
    0.09
    ady
    0.08
    uncate
    0.08
    å·²æĺ¯
    0.08
     onCreateView
    0.08
    èĢĺ
    0.08
    :param
    0.08
    åĥļ
    0.08
    Activations Density 0.010%

    No Known Activations