© 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. 17726
    Prev
    Next
    INDEX
    Explanations

    laid out or laid down

    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
    åħľ
    -0.10
     Bun
    -0.09
    çģ¿
    -0.09
    éŀ£
    -0.08
    çIJĨ解åĴĮ
    -0.08
    å£ħ
    -0.08
    olin
    -0.08
    顼
    -0.08
    éĦ£
    -0.08
    æĪijåıijçİ°
    -0.08
    POSITIVE LOGITS
    交代
    0.10
    夯å®ŀ
    0.10
    æī°
    0.10
    rat
    0.09
    pert
    0.09
     pert
    0.09
     lays
    0.09
    æĦŁè§īèĩªå·±
    0.09
    çģ«çĤ¬
    0.09
    å¥łå®ļäºĨ
    0.09
    Activations Density 0.014%

    No Known Activations