© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38524
    Prev
    Next
    INDEX
    Explanations

    vehicle interior

    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
    å¤ĸå¢Ļ
    -0.11
    -fw
    -0.11
    éĹ®ä»ĸ
    -0.11
    èĢķ
    -0.10
    å·¥ä½ľå²Ĺä½į
    -0.10
    éĻĮ
    -0.10
    èµį
    -0.10
    éªij
    -0.10
    èĩªçĦ¶èĢĮ
    -0.10
    æ§Į
    -0.09
    POSITIVE LOGITS
    车åĨħ
    0.11
     cabin
    0.11
     Cabin
    0.10
    åĨħ饰
    0.10
    座æ¤ħ
    0.10
    Interior
    0.09
     Interior
    0.09
     MMI
    0.09
    欧洲
    0.09
     seating
    0.09
    Activations Density 0.100%

    No Known Activations