© 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. 20863
    Prev
    Next
    INDEX
    Explanations

    Academy of [area of study]

    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
    pering
    -0.10
    èį¡
    -0.09
     Wing
    -0.08
    妥
    -0.08
    bee
    -0.08
    代åĬŀ
    -0.08
    anos
    -0.08
    å¤ļ彩
    -0.08
    滩
    -0.08
    abee
    -0.08
    POSITIVE LOGITS
    éĨ
    0.08
    æ¦ľ
    0.08
     Sed
    0.08
    ä¸Ģè¡Į
    0.08
     Ston
    0.08
    ipi
    0.08
    çĹķ
    0.08
    ipl
    0.08
    tribute
    0.08
    iol
    0.08
    Activations Density 0.013%

    No Known Activations