© 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. 48306
    Prev
    Next
    INDEX
    Explanations

    cars, sedan, sports car

    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
    èįŀ
    -0.10
    èį¤
    -0.10
    пал
    -0.09
    èħ®
    -0.09
    èĥģ
    -0.08
    åĤį
    -0.08
    å¸IJ篷
    -0.08
     FCC
    -0.08
    è´§æŀ¶
    -0.08
    è¢ĭåŃIJ
    -0.08
    POSITIVE LOGITS
    车åŀĭ
    0.11
    æķŀ
    0.11
    æĸ°èĥ½æºIJ
    0.11
    大ä¼Ĺ
    0.11
    æĸ°è½¦
    0.10
     cars
    0.10
    Convertible
    0.10
     sedan
    0.10
     Sed
    0.10
    cars
    0.10
    Activations Density 0.171%

    No Known Activations