© 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. 8889
    Prev
    Next
    INDEX
    Explanations

    existence, being, and condition

    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
    é̏
    -0.11
    æĭĹ
    -0.09
     Rodney
    -0.09
    æľ¬ç½ij
    -0.09
    Vtbl
    -0.09
    åĭº
    -0.09
    èĪĨ论
    -0.09
    å¿ĥè¡Ģ
    -0.09
    è¤Ĥ
    -0.09
    大å±Ģ
    -0.09
    POSITIVE LOGITS
     existential
    0.11
    0
    0.09
    4
    0.09
    2
    0.09
    7
    0.09
    3
    0.09
    8
    0.09
    9
    0.09
    1
    0.09
    6
    0.08
    Activations Density 0.014%

    No Known Activations