© 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. 10543
    Prev
    Next
    INDEX
    Explanations

    swagger generator tool

    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
    ç»Ŀ
    -0.09
    uki
    -0.09
    vore
    -0.09
    çĶļèĩ³è¿ŀ
    -0.09
    .gnu
    -0.08
    oeff
    -0.08
    èĭįçĻ½
    -0.08
    ãĥIJ
    -0.08
    ovel
    -0.08
    ãģķãģ¦
    -0.08
    POSITIVE LOGITS
    лег
    0.09
    æıĸ
    0.09
    pping
    0.09
    ../../../
    0.09
    ception
    0.09
    æĭĪ
    0.09
    åįģ足
    0.09
    å°Ĭ严
    0.09
    pery
    0.08
    满满
    0.08
    Activations Density 0.004%

    No Known Activations