© 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. 1189
    Prev
    Next
    INDEX
    Explanations

    display technologies, chemical compounds

    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
    (lo
    -0.09
    à¸Ńาย
    -0.09
    antro
    -0.09
     Wright
    -0.08
    ermal
    -0.08
     Zoom
    -0.08
    ãĤ¦ãĥ³
    -0.08
    åħĴ
    -0.08
    å¹´è½»
    -0.08
    å¯Ĩ
    -0.08
    POSITIVE LOGITS
    å±±ä¸Ĭ
    0.09
    osp
    0.09
    ovies
    0.09
    çݯçIJĥ
    0.09
    strip
    0.09
    è¿ĩ滤
    0.09
    (filters
    0.08
     доÑĢог
    0.08
    æĻ¯åĮº
    0.08
    æĸ©
    0.08
    Activations Density 0.090%

    No Known Activations