© 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. 22479
    Prev
    Next
    INDEX
    Explanations

    actor and historical names

    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
    é¡¿
    -0.10
    rite
    -0.09
    éłĵ
    -0.09
    èIJ¥
    -0.09
    éĺµ
    -0.09
     Supplement
    -0.09
    åįģæĿ¡
    -0.09
    壮
    -0.08
    çĵ®
    -0.08
     dod
    -0.08
    POSITIVE LOGITS
    çıŃ车
    0.11
    uko
    0.10
    æĬł
    0.10
    享
    0.10
    åł¡
    0.09
     Boeh
    0.09
    cean
    0.09
    loff
    0.09
    çħ§çīĩ
    0.09
    åĿIJçĿĢ
    0.09
    Activations Density 0.034%

    No Known Activations