© 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. 8250
    Prev
    Next
    INDEX
    Explanations

    temple

    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
     Frontier
    -0.10
    çĮ·
    -0.08
     pl
    -0.08
    å½±éŁ³
    -0.08
    æıIJ
    -0.08
    uxt
    -0.08
    çĽIJ
    -0.08
    æĵ¦
    -0.08
    ÑĤи
    -0.08
    omas
    -0.08
    POSITIVE LOGITS
    éħįåģ¶
    0.09
    ç¥Ģ
    0.09
    èł²
    0.09
    éĹ¾
    0.09
    åİŁæľī
    0.09
    datagrid
    0.09
    ä¸įåľ¨
    0.09
     Gods
    0.09
    禳
    0.09
    é¾Ľ
    0.09
    Activations Density 0.048%

    No Known Activations