© 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. 51789
    Prev
    Next
    INDEX
    Explanations

    chlorinated 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
    åĴĮåľ°åĮº
    -0.11
    sWith
    -0.10
    们
    -0.09
     trÄĥm
    -0.09
    lichkeit
    -0.09
    licated
    -0.09
    类产åĵģ
    -0.09
    uls
    -0.08
    .crm
    -0.08
    shelf
    -0.08
    POSITIVE LOGITS
    æ°´ä¸Ń
    0.10
    xygen
    0.09
    lite
    0.09
    구
    0.09
    hex
    0.09
    ine
    0.09
    osed
    0.08
    amines
    0.08
    ther
    0.08
    burgh
    0.08
    Activations Density 0.075%

    No Known Activations