© 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. 48839
    Prev
    Next
    INDEX
    Explanations

    passenger and cargo areas

    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
    hof
    -0.08
    åı°
    -0.08
    æĪIJçĨŁçļĦ
    -0.08
    åĪ©çİĩ
    -0.08
    SENT
    -0.08
    鼷
    -0.08
    æŀ¥
    -0.08
    æĿ¥çļĦ
    -0.08
    é¢Ĩåıĸ
    -0.08
    èĢģ头
    -0.08
    POSITIVE LOGITS
    座ä½į
    0.15
    ä¹ĺåĿIJ
    0.13
    ä¹ĺ客
    0.13
     seating
    0.13
    座æ¤ħ
    0.12
    ä¹ĺ车
    0.11
    çĶ©
    0.11
     passenger
    0.11
    æķŀ
    0.10
    è¶Ł
    0.10
    Activations Density 0.136%

    No Known Activations