© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36657
    Prev
    Next
    INDEX
    Explanations

    digital camera and phone

    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
    çŃ¹èµĦ
    -0.10
    prt
    -0.10
    èŁĭ
    -0.09
    ei
    -0.09
    ä¼ĹçŃ¹
    -0.09
    eve
    -0.09
     Kickstarter
    -0.09
    éľ¹
    -0.08
    常åĬ¡åī¯
    -0.08
    ä¸ĭçıŃ
    -0.08
    POSITIVE LOGITS
    ä¼´ä¾£
    0.09
    odem
    0.09
    åıĭåĸĦ
    0.09
     Spears
    0.09
    ablo
    0.09
     marg
    0.09
    uraa
    0.08
     Margin
    0.08
    avar
    0.08
    å®ļçĤ¹
    0.08
    Activations Density 0.236%

    No Known Activations