© 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. 57517
    Prev
    Next
    INDEX
    Explanations

    bandwidth requirements and utilization

    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
    innen
    -0.10
    ä¹İ
    -0.09
    odor
    -0.09
    yle
    -0.09
    ä¸į该
    -0.09
    ars
    -0.08
    ÈĽi
    -0.08
    çĿĢä»ĸ
    -0.08
    ide
    -0.08
    ylation
    -0.08
    POSITIVE LOGITS
    icc
    0.10
    åįģ足
    0.10
    ür
    0.09
    -tax
    0.09
    ICC
    0.08
    lander
    0.08
    è¿Ļä¸ĢåĪ»
    0.08
    elas
    0.08
    sse
    0.08
    andbox
    0.08
    Activations Density 0.031%

    No Known Activations