© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 7257
    Prev
    Next
    INDEX
    Explanations

    drumming, drum types, and drum machines

    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
    -0.12
    讫
    -0.09
    eger
    -0.09
    /close
    -0.09
    ureka
    -0.08
    çĸļ
    -0.08
    grund
    -0.08
    hood
    -0.08
    éł
    -0.08
    rick
    -0.08
    POSITIVE LOGITS
    istics
    0.11
    ming
    0.11
    mond
    0.10
    igne
    0.10
    zilla
    0.10
    ging
    0.10
    mers
    0.10
    mith
    0.09
    èĩ¾
    0.09
    illo
    0.09
    Activations Density 0.011%

    No Known Activations