© 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
    2. Qwen3-32B
    3. 32-RESID-BATCHTOPK-65K
    4. 8075
    Prev
    Next
    INDEX
    Explanations

    weather conditions and events

    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
    åĵĪ
    -0.09
    onest
    -0.09
    鸥
    -0.08
    èϬ
    -0.08
    æŁľåı°
    -0.08
    çĥŃè¡Ģ
    -0.08
    梳
    -0.08
     оÑĦиÑģ
    -0.08
    欲
    -0.08
    _thr
    -0.08
    POSITIVE LOGITS
     занÑıÑĤ
    0.10
    é¢ijç¹ģ
    0.09
    ä»İåݻ年
    0.09
    éķĩåħļå§Ķ
    0.09
    éĻĤ
    0.09
    à¸Īà¸Ļ
    0.09
    æĢ
    0.09
    çĭłçĭł
    0.08
    brero
    0.08
    è¿ij两年
    0.08
    Activations Density 0.035%

    No Known Activations