© 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. 5399
    Prev
    Next
    INDEX
    Explanations

    majority vote outcomes

    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
    ä½Ŀ
    -0.09
     Joh
    -0.09
    ä»ģ
    -0.09
    è¿Ħ
    -0.09
    .tpl
    -0.08
    ulong
    -0.08
    ä¸Ĭå®ĺ
    -0.08
    ä¼ļä¼ļéķ¿
    -0.08
    ä¸įåı¯éģ¿åħį
    -0.08
    ç»ĵå±Ģ
    -0.08
    POSITIVE LOGITS
     majority
    0.15
     Majority
    0.13
    å¤ļæķ°
    0.11
    ä¸ĢåįĬ
    0.11
     половин
    0.09
    åįłæľīçİĩ
    0.09
     ÐijолÑĮ
    0.09
     mayorÃŃa
    0.09
    çĵ´
    0.09
    ä¸īåĪĨä¹ĭä¸Ģ
    0.09
    Activations Density 0.041%

    No Known Activations