© 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. 20862
    Prev
    Next
    INDEX
    Explanations

    professionalism and professionalism

    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
    å®īå±ħ
    -0.10
    åħŃåIJĪ
    -0.09
     полÑĮз
    -0.09
    æķ¦
    -0.08
    ngo
    -0.08
    æı´åĬ©
    -0.08
    uchs
    -0.08
    TB
    -0.08
    åĿļä¿¡
    -0.08
    æĭĮ
    -0.08
    POSITIVE LOGITS
    æĢģ度
    0.14
    çļĦæĢģ度
    0.13
    æ°´åĩĨ
    0.12
    åįģ足
    0.11
    对å¾ħ
    0.11
    èĻ
    0.10
    ism
    0.10
    æ¶ķ
    0.10
    æħĭ度
    0.10
     ÙĦÙĦغاÙĬØ©
    0.10
    Activations Density 0.013%

    No Known Activations