© 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. 31947
    Prev
    Next
    INDEX
    Explanations

    Archbishop or bishop

    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
    hape
    -0.09
    oration
    -0.09
    绨
    -0.08
    æĻ°
    -0.08
    нак
    -0.08
    çŁ³èĨı
    -0.08
    nier
    -0.08
    adder
    -0.08
    åįģ足
    -0.08
    æĪIJåŀĭ
    -0.08
    POSITIVE LOGITS
    诰
    0.11
    åħ¼
    0.10
    ness
    0.10
    ฯ
    0.09
    ï¸
    0.09
    -push
    0.09
    acen
    0.09
    æ»Ķ
    0.08
    lington
    0.08
    Steam
    0.08
    Activations Density 0.016%

    No Known Activations