© 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. 33803
    Prev
    Next
    INDEX
    Explanations

    contractions with following words

    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
    åĪĽéĢłåĬĽ
    -0.10
    åĪ¶
    -0.09
    ,ep
    -0.08
    çŁ³æ¦´
    -0.08
    tur
    -0.08
    年人
    -0.08
    æłĵ
    -0.08
    зов
    -0.08
     McCabe
    -0.08
    åij¼å£°
    -0.08
    POSITIVE LOGITS
    è°¢
    0.09
    audi
    0.09
    kes
    0.09
    æīĭèħķ
    0.09
    èĭĩ
    0.09
    alytics
    0.08
    æľįåĬ¡äºİ
    0.08
     ê·¸ëłĩ
    0.08
    å¹ķ
    0.08
     ׾×ŀ×Ļ
    0.08
    Activations Density 0.127%

    No Known Activations