© 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. 53384
    Prev
    Next
    INDEX
    Explanations

    District Attorney's Office

    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
    erness
    -0.10
    tmpl
    -0.10
    جÙĬر
    -0.09
    lage
    -0.09
    æĦıä¹īä¸ĬçļĦ
    -0.08
    çīĩ
    -0.08
    çĶŁæĢķ
    -0.08
    ICENSE
    -0.08
    apan
    -0.08
    人家
    -0.08
    POSITIVE LOGITS
    åĥ®
    0.09
     geli
    0.09
     mate
    0.09
     leggings
    0.08
    amar
    0.08
    cheid
    0.08
    UFF
    0.08
    blink
    0.08
    /media
    0.07
    witch
    0.07
    Activations Density 0.012%

    No Known Activations