© 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. 27868
    Prev
    Next
    INDEX
    Explanations

    verb followed by noun/adjective

    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
    åį»
    -0.09
    åį´
    -0.08
    EventData
    -0.08
     Gang
    -0.08
    ä¹ŁæĪIJ为
    -0.08
    ä½Ĩåį´
    -0.08
    åį´åıĪ
    -0.08
    atas
    -0.08
    organ
    -0.07
    åį´ä¸į
    -0.07
    POSITIVE LOGITS
    ngth
    0.10
    åľ¨æĪijçļĦ
    0.10
    æµģ浪
    0.09
    æĪIJå°±æĦŁ
    0.09
     ÙĪضع
    0.08
    éĩİçĶŁ
    0.08
    说æĪij
    0.08
    ØŃÙħ
    0.08
    æ¸ħé¦Ļ
    0.08
    çĶ¨éĩı
    0.08
    Activations Density 0.104%

    No Known Activations