© 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. 51807
    Prev
    Next
    INDEX
    Explanations

    lustrous shine

    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
    æīĢ以说
    -0.09
    åĵĪåĵĪ
    -0.09
    iece
    -0.09
     Toe
    -0.09
    .strict
    -0.08
    æ¡ĮåŃIJ
    -0.08
    åıijåĬ¨
    -0.08
    ×ļ
    -0.08
    åĪ©åĻ¨
    -0.08
    é¥Ń
    -0.08
    POSITIVE LOGITS
    çŃī级
    0.09
    tá
    0.08
    ous
    0.08
    åįģ足
    0.08
    æķĪæŀľ
    0.08
    第ä¸ĢåIJį
    0.08
    _filenames
    0.08
    inx
    0.08
    brace
    0.08
    æĦŁ
    0.08
    Activations Density 0.007%

    No Known Activations