© 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. 53411
    Prev
    Next
    INDEX
    Explanations

    collaboration and partnership between entities

    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
    éªĬ
    -0.12
    çĶ°éĩİ
    -0.10
    еÑģп
    -0.10
    æľīèĩªå·±çļĦ
    -0.10
    åŀŃ
    -0.09
    缣
    -0.09
    ician
    -0.09
    èĪ¸
    -0.09
    loyment
    -0.09
     Soros
    -0.09
    POSITIVE LOGITS
     effort
    0.11
    ä¹İ
    0.10
    å¤ļæĸ¹
    0.09
    3
    0.09
    2
    0.09
    åĩłä¸ª
    0.09
    ç»ĻäºĨæĪij
    0.09
    1
    0.09
    å¤ļ个
    0.09
    åħŃ大
    0.09
    Activations Density 0.040%

    No Known Activations