© 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. 4901
    Prev
    Next
    INDEX
    Explanations

    ear piercing and auricular

    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
    stamp
    -0.10
    ä¼ı
    -0.09
    azy
    -0.09
    bol
    -0.09
    çĻŀ
    -0.09
    oulder
    -0.09
    дов
    -0.08
    _ARB
    -0.08
    ä¸įçķĻ
    -0.08
    é¢ĦåħĪ
    -0.08
    POSITIVE LOGITS
     pierced
    0.10
    çīµ
    0.09
     piercing
    0.09
    Lane
    0.09
     pier
    0.09
    æĮij
    0.09
    è´¯
    0.09
    .descriptor
    0.08
    ç²
    0.08
    é²ģè¿ħ
    0.08
    Activations Density 0.036%

    No Known Activations