© 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. 21262
    Prev
    Next
    INDEX
    Explanations

    emotion

    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
    ï¸
    -0.11
    side
    -0.09
    igin
    -0.08
    ness
    -0.08
    istan
    -0.08
    mentation
    -0.08
    TURE
    -0.08
    baum
    -0.08
    ìĦ¬
    -0.08
    æŃ£æĸĩ
    -0.08
    POSITIVE LOGITS
    ality
    0.12
    nelle
    0.12
    ally
    0.12
    als
    0.10
    nel
    0.10
    ALLY
    0.10
    ilda
    0.10
     педагог
    0.10
    ftware
    0.09
    nal
    0.09
    Activations Density 0.004%

    No Known Activations