© 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. 37987
    Prev
    Next
    INDEX
    Explanations

    voices heard expressing feelings

    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
    缼
    -0.10
    åħīçݯ
    -0.10
    åĿŀ
    -0.10
    æĪij们ä¸Ģèµ·
    -0.09
     Bose
    -0.09
    éº»æľ¨
    -0.09
    ä¸īä½įä¸Ģä½ĵ
    -0.09
    çľ¯
    -0.09
    å¤ļä½į
    -0.09
    çļĦåĪ©çĽĬ
    -0.09
    POSITIVE LOGITS
    æĦŁåıĹåĪ°
    0.10
    åĪ°åľº
    0.09
     Provid
    0.09
     presence
    0.09
    QL
    0.09
    ä¸įåĩº
    0.09
    ç«ĭåĪ»
    0.09
    omba
    0.09
    arters
    0.08
    .languages
    0.08
    Activations Density 0.054%

    No Known Activations