© 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. 31390
    Prev
    Next
    INDEX
    Explanations

    Henderson and Hend variations

    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
    bomb
    -0.11
    anky
    -0.09
    urgeon
    -0.09
    èįı
    -0.09
     اÙĦزÙħÙĨ
    -0.09
    ------------------------------------------------------------------------------------------------
    -0.09
    วà¸Ļ
    -0.09
    walking
    -0.09
    è¿Ļæł·çļĦè¯Ŀ
    -0.09
    prm
    -0.09
    POSITIVE LOGITS
    ä¸įäºĨ
    0.09
    OrUpdate
    0.09
    azole
    0.08
    thal
    0.08
    antly
    0.08
     polished
    0.08
    4
    0.08
    atory
    0.08
    ance
    0.08
    icator
    0.08
    Activations Density 0.009%

    No Known Activations