© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51213
    Prev
    Next
    INDEX
    Explanations

    bargain and agreement

    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
    zens
    -0.09
    è´«åĽ°æĿij
    -0.09
    elman
    -0.09
    aque
    -0.09
    acula
    -0.08
    å°ı康
    -0.08
    íĹĪ
    -0.08
    uality
    -0.08
    è¦ģæĬĬ
    -0.08
    æļĸæ°Ķ
    -0.08
    POSITIVE LOGITS
    ony
    0.10
    å²Ļ
    0.09
    ouv
    0.09
    æĸ¯åŁº
    0.09
    ora
    0.09
    trys
    0.09
    asser
    0.08
    าย
    0.08
    ewe
    0.08
    ry
    0.08
    Activations Density 0.004%

    No Known Activations