© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 51923
    Prev
    Next
    INDEX
    Explanations

    Realtor or Realty

    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
    mant
    -0.09
    æ²Ķ
    -0.09
    è¡
    -0.08
    kowski
    -0.08
     *&
    -0.08
    åĬ¿
    -0.08
    CommandLine
    -0.08
    ç»
    -0.08
    çī¹éĤĢ
    -0.08
    ovation
    -0.08
    POSITIVE LOGITS
    èģĮä¸ļéģĵå¾·
    0.09
     pisc
    0.08
    VIC
    0.08
    rega
    0.08
    éªĹåıĸ
    0.08
    Ìģ
    0.08
    æľĭåıĭ
    0.08
    空éĹ´
    0.08
    odelist
    0.08
    uchs
    0.08
    Activations Density 0.003%

    No Known Activations