© 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. 52312
    Prev
    Next
    INDEX
    Explanations

    uncertainty about future expectations

    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
    åĿĬ
    -0.11
    .arg
    -0.09
    æĪij认为
    -0.09
    beck
    -0.08
    ä¸įå¿ħ
    -0.08
    avian
    -0.08
    追
    -0.08
    è¦Ĩ
    -0.08
    ä¸įéľĢè¦ģ
    -0.08
    DefaultValue
    -0.08
    POSITIVE LOGITS
    ä¹Łä¸įçŁ¥éģĵ
    0.14
    ä¹Łä¸įæķ¢
    0.12
    åıªçŁ¥éģĵ
    0.12
    æľªçŁ¥
    0.11
    好åĿı
    0.10
    ä¸įæ¸ħæ¥ļ
    0.10
    oods
    0.10
    æľīä»»ä½ķ
    0.10
    åıijå±ķæĸ¹åIJij
    0.10
     nor
    0.10
    Activations Density 0.055%

    No Known Activations