© 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. 32578
    Prev
    Next
    INDEX
    Explanations

    continental / continents

    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
     налиÑĩ
    -0.09
    å¿ĥå¾Ĺ
    -0.09
    teenth
    -0.09
    åķī
    -0.08
    ä¸įå°½
    -0.08
     Scarlet
    -0.08
    è¾ĸåĮºåĨħ
    -0.08
    åĨ·
    -0.08
     dint
    -0.08
     Intent
    -0.08
    POSITIVE LOGITS
    ä¹İ
    0.11
    arity
    0.11
    izer
    0.11
    iates
    0.10
    ANCE
    0.10
    loh
    0.10
    izing
    0.09
    幸
    0.09
    ised
    0.09
    empor
    0.09
    Activations Density 0.014%

    No Known Activations