© 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. 35327
    Prev
    Next
    INDEX
    Explanations

    filibuster, recall, confirmation, vote

    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
    piler
    -0.10
    ToEnd
    -0.09
    chet
    -0.09
    gger
    -0.09
    hiba
    -0.09
    oblin
    -0.09
     Arbor
    -0.08
    çļĦæ¯ĶèµĽ
    -0.08
    çħ§æĸĻ
    -0.08
    ERT
    -0.08
    POSITIVE LOGITS
    acy
    0.10
    dar
    0.09
     ÙĪØ£ÙĨ
    0.09
    大åĨĽ
    0.08
    åĢĻ
    0.08
    éĢļä¿Ĺ
    0.08
    ish
    0.08
    аÑĢа
    0.08
    ocy
    0.08
    è¿ĩçļĦ
    0.08
    Activations Density 0.004%

    No Known Activations