© 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. 18763
    Prev
    Next
    INDEX
    Explanations

    mathematician or university

    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
    åĵģç±»
    -0.09
     monopol
    -0.08
    粤
    -0.08
    ç½ijæ°ij
    -0.08
    åıĸè¯ģ
    -0.07
    itud
    -0.07
    顺德
    -0.07
    æĬµ
    -0.07
     fur
    -0.07
    åģĩ
    -0.07
    POSITIVE LOGITS
    æķ°åѦ
    0.12
    严å¯Ĩ
    0.10
    æ±
    0.09
     mathematic
    0.09
     Sleeping
    0.09
     mathematics
    0.09
    æĻºåĬĽ
    0.09
    "math
    0.09
    æĬĸ
    0.08
    å²ģ以ä¸ĭ
    0.08
    Activations Density 1.452%

    No Known Activations