© 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. 8428
    Prev
    Next
    INDEX
    Explanations

    visual cortex, temporal, magnocellular

    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
    åľĺ
    -0.09
    igel
    -0.08
     alum
    -0.08
    两家
    -0.08
    ç´§å¯Ĩ
    -0.08
    é¹Ī
    -0.08
    éŃĤ
    -0.08
    å¸ĤæķĻèĤ²
    -0.08
    亲çα
    -0.08
    æķĿ
    -0.08
    POSITIVE LOGITS
     Harvey
    0.09
    æ¶ij
    0.09
     shel
    0.09
    ä¸ĵåľº
    0.09
    ç»ĺ
    0.09
     Nem
    0.08
    леÑĤ
    0.08
    ç¼ĸçłģ
    0.08
    èĥĮåıĽ
    0.08
    æĭ¾
    0.08
    Activations Density 0.235%

    No Known Activations