© 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. 37369
    Prev
    Next
    INDEX
    Explanations

    since [time period]

    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
    ä»ĭ
    -0.09
    éļĻ
    -0.08
    Detect
    -0.08
     presently
    -0.08
    æľĢæĸ°
    -0.08
    è¿ĻæĿ¡
    -0.08
    unden
    -0.07
     slip
    -0.07
    rng
    -0.07
     Siri
    -0.07
    POSITIVE LOGITS
    åİĨåı²ä¸Ĭ
    0.10
    å¹ħ度
    0.10
    年代
    0.09
    éĩįè§Ĩ
    0.09
     اÙĦÙĤرÙĨ
    0.09
    çļĦéĩį大
    0.09
    çļĦåİĨåı²
    0.09
    åı¦ä¸Ģä½į
    0.09
    åĬŀäºĭ
    0.09
     hiếm
    0.09
    Activations Density 0.062%

    No Known Activations