© 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. 52137
    Prev
    Next
    INDEX
    Explanations

    music albums

    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
    lessly
    -0.11
    fully
    -0.10
    lessness
    -0.10
    åįģ足
    -0.09
    lings
    -0.09
     dÃłng
    -0.09
     kiá»ĩn
    -0.09
    oks
    -0.09
    ListOf
    -0.09
    obb
    -0.09
    POSITIVE LOGITS
    inous
    0.10
    éĵĽ
    0.10
    anes
    0.10
    mates
    0.10
    oug
    0.09
    rium
    0.09
    worm
    0.09
    (AL
    0.09
    \Query
    0.09
    sek
    0.09
    Activations Density 0.029%

    No Known Activations