© 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. 48271
    Prev
    Next
    INDEX
    Explanations

    application and reviewing processes

    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
    orient
    -0.09
    å¼ķé¢Ĩ
    -0.09
    roc
    -0.09
    ç¬ij声
    -0.08
    ä¸ļæĢģ
    -0.08
    ãģ£ãģ½
    -0.08
    æŃ£éĿ¢
    -0.08
    oods
    -0.08
    èĥ¸åīį
    -0.08
    åºŁè¯Ŀ
    -0.08
    POSITIVE LOGITS
    å¥ĸåѦéĩij
    0.11
    åıĪè¦ģ
    0.10
    æĭĽçĶŁ
    0.10
    æĻļ
    0.10
    å°½æĹ©
    0.09
     Timing
    0.09
     леÑĤ
    0.09
    .portal
    0.09
    éĢĴ交
    0.09
    纵
    0.09
    Activations Density 0.020%

    No Known Activations