© 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. 57706
    Prev
    Next
    INDEX
    Explanations

    reaching epidemic proportions

    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
     createContext
    -0.09
    aroo
    -0.08
    ç»Ĩèħ»
    -0.08
    æĺ¯æľĢ好çļĦ
    -0.08
    .softmax
    -0.08
    Æ°á»Ľng
    -0.08
    大èĩ´
    -0.08
    bag
    -0.08
    大约
    -0.08
     Tul
    -0.08
    POSITIVE LOGITS
    åı²è¯Ĺ
    0.11
     proportions
    0.11
    åĽĽæĸ¹
    0.10
    -scale
    0.10
     amounts
    0.10
    ÙħصÙĦ
    0.09
    ä¼Ł
    0.09
    ONA
    0.09
    éķij
    0.09
    ä¼ļ让
    0.09
    Activations Density 0.040%

    No Known Activations