© 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. 11994
    Prev
    Next
    INDEX
    Explanations

    years before 1958

    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
    æł¸å¿ĥæĬĢæľ¯
    -0.11
    æĪĹ
    -0.09
    umped
    -0.09
    éĶľ
    -0.09
    ÙĦع
    -0.09
     RELATED
    -0.08
    轺
    -0.08
     ÑĪиÑĢоко
    -0.08
    æĪĺæĸĹ
    -0.08
    ueue
    -0.08
    POSITIVE LOGITS
    AMA
    0.11
     Orr
    0.09
    -style
    0.09
    OM
    0.08
    arme
    0.08
    æł¡åıĭ
    0.08
     Tradition
    0.08
    anner
    0.07
    y
    0.07
     active
    0.07
    Activations Density 0.159%

    No Known Activations