© 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. 2976
    Prev
    Next
    INDEX
    Explanations

    partnership and collaboration

    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
    è±ģ
    -0.09
     Ansi
    -0.09
    pedia
    -0.09
    ta
    -0.08
    æĢĢ
    -0.08
    éļ¾æ°ij
    -0.08
    (em
    -0.08
    nap
    -0.08
     Abed
    -0.08
    å¼
    -0.08
    POSITIVE LOGITS
    åIJĪä½ľåħ³ç³»
    0.21
    åIJĪä½ľ
    0.20
     partnership
    0.16
     partnerships
    0.16
    åIJĪä½ľä¼Ļä¼´
    0.15
    çļĦåIJĪä½ľ
    0.15
     partners
    0.15
     collaboration
    0.15
     partner
    0.14
     cooperation
    0.14
    Activations Density 0.148%

    No Known Activations