© 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. 32037
    Prev
    Next
    INDEX
    Explanations

    vulnerable populations and conditions

    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
    佬
    -0.13
    º
    -0.11
    eh
    -0.10
    槿
    -0.10
    çĭIJ
    -0.09
    el
    -0.09
    èĩ¾
    -0.09
    aller
    -0.09
    an
    -0.09
    erv
    -0.09
    POSITIVE LOGITS
    æľŁåĨħ
    0.10
    esson
    0.10
    azon
    0.10
    å¤ł
    0.10
    lü
    0.09
    aise
    0.09
    æĢ§å¼º
    0.09
    åľ°å¸¦
    0.09
    ields
    0.09
    åľ¨äºİ
    0.08
    Activations Density 0.011%

    No Known Activations