© 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. 5362
    Prev
    Next
    INDEX
    Explanations

    vehicle-related systems

    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
    ä¼ļéķ¿
    -0.09
    è¨ĢãģĦ
    -0.08
    éķ¿èĢģ
    -0.08
    åī¯ä¼ļéķ¿
    -0.08
    å±Ģéķ¿
    -0.08
    们
    -0.08
     cog
    -0.08
    åİ¿å§Ķ书记
    -0.08
    åIJĮäºĭ
    -0.08
    天ä¸ĭ
    -0.08
    POSITIVE LOGITS
    æķ´ä½ĵ
    0.13
    -wide
    0.12
    çļĦæķ´ä½ĵ
    0.11
    wide
    0.10
    æĢ»ä½ĵ
    0.10
    åĨħçļĦ
    0.09
    çݰ身
    0.09
    /course
    0.09
    çݯå¢ĥä¸Ń
    0.08
    ä¸Ńæĸ°
    0.08
    Activations Density 0.782%

    No Known Activations