© 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. 7767
    Prev
    Next
    INDEX
    Explanations

    dwarfism and dwarf galaxies

    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
    istor
    -0.10
    wipe
    -0.09
    éĩİçĶŁåĬ¨çī©
    -0.09
    abr
    -0.09
    и
    -0.09
    ModelProperty
    -0.09
     Watkins
    -0.09
    å¤ĸåĽ½äºº
    -0.09
    /lgpl
    -0.09
    wards
    -0.09
    POSITIVE LOGITS
    ling
    0.11
    hood
    0.11
    ing
    0.10
     Trev
    0.09
    æģ¨ä¸įå¾Ĺ
    0.09
    lings
    0.09
     Bett
    0.09
    eldorf
    0.09
    /min
    0.09
    аÑħ
    0.09
    Activations Density 0.009%

    No Known Activations