© 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. 2064
    Prev
    Next
    INDEX
    Explanations

    parent/child relationships; new/old things

    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
    ä¸įä»ħæĺ¯
    -0.09
    èĢĮä¸įæĺ¯
    -0.09
    è¤Ĵ
    -0.09
    欸
    -0.08
    森æŀĹåħ¬åĽŃ
    -0.08
    дÑĢа
    -0.08
    å°±æĺ¯è¿Ļæł·
    -0.08
    ä¸įåıªæĺ¯
    -0.08
    第äºĮ个
    -0.08
    ä¸įæĺ¯ä¸Ģ个
    -0.08
    POSITIVE LOGITS
     ones
    0.23
     Ones
    0.15
     counterparts
    0.11
    ãģªãĤĤãģ®
    0.10
    ones
    0.09
     counterpart
    0.09
    åį»
    0.09
    åĨįåĪ°
    0.09
    ä½ľä¸ºä¸ĢåIJį
    0.09
    ãģ»ãģĨ
    0.09
    Activations Density 0.667%

    No Known Activations