© 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. 21090
    Prev
    Next
    INDEX
    Explanations

    eocene, miocene, pleistocene, age

    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
    å®Ī
    -0.12
    ippy
    -0.10
    æIJĤ
    -0.09
    cratch
    -0.09
     Lines
    -0.09
     ÐĽÐ¸
    -0.09
    ç»»
    -0.09
    å½±
    -0.09
    ourg
    -0.08
    rov
    -0.08
    POSITIVE LOGITS
    æĹ¶æľŁçļĦ
    0.10
    çĻ¾äº¿
    0.09
    åĴĨ
    0.09
     pre
    0.09
    çģŃ
    0.09
    æ¯Ľ
    0.09
    碳éħ¸
    0.09
    è¿ĩåİ»çļĦ
    0.09
    åľ°è´¨
    0.09
    çļĵ
    0.09
    Activations Density 0.094%

    No Known Activations