© 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. 8483
    Prev
    Next
    INDEX
    Explanations

    claims or preamble

    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
     Doub
    -0.08
     Bee
    -0.08
    å´ĩå°ļ
    -0.08
    oples
    -0.08
     spot
    -0.08
     Columbus
    -0.08
     pole
    -0.08
     suất
    -0.08
     times
    -0.08
    åĸľæĤ¦
    -0.08
    POSITIVE LOGITS
    ä¸ĢåŃĹ
    0.09
    _FLASH
    0.09
    æĭ±
    0.09
    çħ®
    0.08
    åħįè´£
    0.08
    èĺijèıĩ
    0.08
    åĪĨæĺİ
    0.08
    çķĮå®ļ
    0.08
    /goto
    0.08
     claim
    0.08
    Activations Density 0.145%

    No Known Activations