© 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. 11191
    Prev
    Next
    INDEX
    Explanations

    comparison and comparing

    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
    heit
    -0.10
    ä¸ĭå·´
    -0.09
    æ£ĭ
    -0.09
    loid
    -0.09
    ë¦Ħ
    -0.08
     Maiden
    -0.08
     Jord
    -0.08
     ÙĪاضØŃ
    -0.08
    ELS
    -0.08
    çļĦæĦıæĢĿ
    -0.08
    POSITIVE LOGITS
    对æ¯Ķ
    0.29
     comparison
    0.25
     compare
    0.25
    .compare
    0.23
     comparing
    0.23
    compare
    0.22
     compares
    0.22
     comparisons
    0.22
    comparison
    0.22
     ÑģÑĢав
    0.22
    Activations Density 0.310%

    No Known Activations