© 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. 9152
    Prev
    Next
    INDEX
    Explanations

    atoxic, aloe"

    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
    é¹Ń
    -0.10
    åħīéĺ´
    -0.10
    eger
    -0.09
    æѧ
    -0.08
    ä¸Ģ对ä¸Ģ
    -0.08
    à¦
    -0.08
     Jason
    -0.08
    chè
    -0.08
    çİ°å®ŀ
    -0.08
    æľĿ
    -0.08
    POSITIVE LOGITS
    说åĩº
    0.09
    主ä¹ī
    0.09
    佩æľį
    0.08
    侧ç»ĵæŀĦæĢ§
    0.08
    æĢ§çĸ¾çĹħ
    0.08
    busters
    0.08
    å§Ķä¼ļ
    0.08
    ายà¸Ļ
    0.08
    åij½
    0.08
    æīĵåĩº
    0.08
    Activations Density 0.765%

    No Known Activations