© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 8413
    Prev
    Next
    INDEX
    Explanations

    milk and milk powder

    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
    essed
    -0.10
    ellt
    -0.09
    er
    -0.09
    ess
    -0.09
    .Creator
    -0.08
    ä½ŀ
    -0.08
     Dame
    -0.08
    ãĤĭãĤĤãģ®
    -0.08
    穹
    -0.08
    à¤ĩ
    -0.08
    POSITIVE LOGITS
    shake
    0.14
    maids
    0.11
    maid
    0.10
    otte
    0.10
    озв
    0.10
    weed
    0.09
    onomies
    0.09
    scribe
    0.09
    оп
    0.09
    辩è¯ģ
    0.08
    Activations Density 0.017%

    No Known Activations