© 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. 33577
    Prev
    Next
    INDEX
    Explanations

    corticosteroids

    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
    omm
    -0.12
    å·²ä¹ħçļĦ
    -0.10
    idget
    -0.10
    mdp
    -0.09
    åı£æ°Ķ
    -0.08
    ä¸Ĭå¹´
    -0.08
    jur
    -0.08
    åŁŃ
    -0.08
    ertz
    -0.08
    ä¸ĵå±ŀ
    -0.08
    POSITIVE LOGITS
    æł·çļĦ
    0.09
    à¹Ģà¸ĸ
    0.09
    ä¸į足
    0.08
    çĶŁçĶŁ
    0.08
    ÙĨÙĬØ©
    0.08
     Kushner
    0.08
    æªĢ
    0.08
    czy
    0.08
    este
    0.08
    èIJ¼
    0.08
    Activations Density 0.052%

    No Known Activations