© 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. 21263
    Prev
    Next
    INDEX
    Explanations

    volleyball

    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
     Isaac
    -0.10
    岿
    -0.10
    æĿĢ
    -0.09
    iclass
    -0.08
    heit
    -0.08
    rit
    -0.08
    ç¨İè´¹
    -0.08
    ÏĬ
    -0.08
    ry
    -0.08
    .grp
    -0.08
    POSITIVE LOGITS
    eros
    0.10
    ç´¯äºĨ
    0.10
    å§Ķ
    0.10
    orda
    0.09
    ä¿Ĺ
    0.09
    ãģ«åĩº
    0.09
    uem
    0.08
    hoff
    0.08
     sor
    0.08
    羣çIJĨ
    0.08
    Activations Density 0.006%

    No Known Activations