© 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. 23414
    Prev
    Next
    INDEX
    Explanations

    finding a store, home, or deals

    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
    éģ²
    -0.09
    CTION
    -0.09
    æļ¹
    -0.09
    èĩªçĦ¶èĢĮ
    -0.08
    ait
    -0.08
    äºĮ线
    -0.08
    建ç«ĭäºĨ
    -0.08
    Trivia
    -0.08
    iset
    -0.08
    hai
    -0.08
    POSITIVE LOGITS
    VAS
    0.09
    rics
    0.09
    çĶŁæ´»çļĦ
    0.08
    ä¸ĩäºĭ
    0.08
     jobs
    0.08
    ä¼´ä¾£
    0.08
    å±¥
    0.08
    yscale
    0.08
    ewater
    0.08
    åŁİå¸ĤçļĦ
    0.08
    Activations Density 0.009%

    No Known Activations