© 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. 53428
    Prev
    Next
    INDEX
    Explanations

    forms of "to be" followed by verbs

    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
    èĩªåľ¨
    -0.11
    æĿĸ
    -0.10
    å¼Ł
    -0.09
    çħ§æĸĻ
    -0.09
     Muss
    -0.09
    åĭŁéĽĨèµĦéĩij
    -0.08
    å¥Ķé©°
    -0.08
    åij·
    -0.08
     Tol
    -0.08
    ì¹ł
    -0.08
    POSITIVE LOGITS
    åĪĨåĪ«æĺ¯
    0.11
    æĪĸå°Ĩ
    0.09
    è£ģåĪ¤
    0.09
    责任ç¼ĸè¾ij
    0.08
    èµĽ
    0.08
    å½ĵ代
    0.08
    /ws
    0.08
    -sdk
    0.08
    angelog
    0.08
    ä¿Ĺ
    0.08
    Activations Density 0.099%

    No Known Activations