© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 3674
    Prev
    Next
    INDEX
    Explanations

    bay area, bayou, bayesian

    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
    æĬ±åĽ¢
    -0.10
    mel
    -0.09
    累累
    -0.09
    çĥŃéĩı
    -0.09
    ç®Ķ
    -0.09
    æĵĤ
    -0.09
    åįİåĮĹ
    -0.09
    æĪ¢
    -0.08
    .border
    -0.08
    人åĿĩ
    -0.08
    POSITIVE LOGITS
    åģļåĪ°äºĨ
    0.10
    è³
    0.09
    符
    0.09
    floor
    0.08
    à¹ģว
    0.08
    .INPUT
    0.08
    culate
    0.08
    rab
    0.08
    ruz
    0.08
     ÑģпÑĢав
    0.08
    Activations Density 0.006%

    No Known Activations