© 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. 49049
    Prev
    Next
    INDEX
    Explanations

    gas concentration measurement

    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
    æĢĥ
    -0.09
    Knight
    -0.08
    ion
    -0.08
     Injection
    -0.08
    磨æįŁ
    -0.08
    ä¸įå¤ļ
    -0.08
     factorial
    -0.08
     gn
    -0.08
    ä¿®å¤į
    -0.07
     огÑĢани
    -0.07
    POSITIVE LOGITS
    æ°Ķä½ĵ
    0.12
    æľīæ¯Ĵ
    0.11
    æ°Ķæ°Ľ
    0.11
    ä¸Ńæ¯Ĵ
    0.11
    æ°Ľ
    0.11
    æ°Ķè´¨
    0.11
    çĨı
    0.10
    æ£Ģæµĭ
    0.10
    æĬ¥èѦ
    0.10
    ç¥
    0.10
    Activations Density 0.139%

    No Known Activations