© 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. 7978
    Prev
    Next
    INDEX
    Explanations

    expressing expectation or thought

    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
    auc
    -0.10
    å®ŀéĻħä¸Ĭæĺ¯
    -0.09
    éŃĦ
    -0.09
     currently
    -0.09
    åĽļ
    -0.09
    bos
    -0.08
    å®ŀéĻħä¸Ĭ
    -0.08
    æķ¬è¯·
    -0.08
    segue
    -0.08
    åĪ°åºķ
    -0.08
    POSITIVE LOGITS
     ÙħØŃÙħ
    0.10
    _flg
    0.09
    å·²ä¹ħçļĦ
    0.09
     rằng
    0.09
    ses
    0.09
    ibern
    0.09
    (hidden
    0.08
    æĬĵç´§
    0.08
     ÑĢан
    0.08
    pson
    0.08
    Activations Density 0.024%

    No Known Activations