© 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. 19494
    Prev
    Next
    INDEX
    Explanations

    body or bodies

    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
    istan
    -0.10
    pery
    -0.10
    ery
    -0.10
    etty
    -0.10
     деÑĤи
    -0.10
    crest
    -0.10
    iator
    -0.10
    виÑĤ
    -0.09
    atter
    -0.09
    imal
    -0.09
    POSITIVE LOGITS
    guards
    0.12
    hood
    0.11
     politic
    0.11
    åĨħçļĦ
    0.10
    é¨
    0.10
    åŃ¦å®¶
    0.10
    èij¬
    0.10
    t
    0.09
    æľºèĥ½
    0.09
    ç´łè´¨
    0.09
    Activations Density 0.069%

    No Known Activations