© 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. 53661
    Prev
    Next
    INDEX
    Explanations

    integrating software systems and information

    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
    èĩªæķij
    -0.10
    å¼ķ导
    -0.10
    ç¼
    -0.09
    车åĨħ
    -0.09
    utsch
    -0.09
    esa
    -0.09
    æŶæĬ¥
    -0.09
    _EV
    -0.09
    è°ĭ
    -0.09
    ç¼ł
    -0.09
    POSITIVE LOGITS
    æĹłç¼Ŀ
    0.10
    æķ´åIJĪ
    0.10
    å¤ĸåĽ´
    0.09
    主æµģ
    0.09
    ën
    0.09
    å¤ĸéĥ¨
    0.09
    Integration
    0.08
    åIJIJ
    0.08
     seamlessly
    0.08
    è¿ĽæĿ¥
    0.08
    Activations Density 0.254%

    No Known Activations