© 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. 49394
    Prev
    Next
    INDEX
    Explanations

    vegetables and salads

    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
     rap
    -0.09
    rsp
    -0.09
    é¢ł
    -0.08
    reh
    -0.08
    rip
    -0.08
    alar
    -0.08
     Allen
    -0.08
    Allen
    -0.08
     anchor
    -0.08
    ä¸įä¸Ĭ
    -0.08
    POSITIVE LOGITS
    hardt
    0.10
    lung
    0.09
    åħ¬åŃIJ
    0.09
    èĬĭ
    0.09
    磾
    0.09
    èĩ¾
    0.09
    纳æĸ¯
    0.09
    èĬ©
    0.09
    iter
    0.09
    çķĮçļĦ
    0.09
    Activations Density 0.004%

    No Known Activations