© 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. 55140
    Prev
    Next
    INDEX
    Explanations

    USA followed by news, legal, or network terms

    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
     McM
    -0.09
    ç«
    -0.08
    èĦļä¸ĭ
    -0.08
    èģļä¼ļ
    -0.08
    umer
    -0.08
     Allison
    -0.08
    erals
    -0.08
    麻辣
    -0.08
    åIJ¯ç¤º
    -0.08
    çݯå¢ĥ污æŁĵ
    -0.07
    POSITIVE LOGITS
    alc
    0.10
    ourt
    0.10
    .Features
    0.09
    Å¡t
    0.09
    mere
    0.09
    NIC
    0.09
     Canc
    0.09
    å¾¼
    0.09
    ç¿ķ
    0.09
    PLEX
    0.09
    Activations Density 0.006%

    No Known Activations