© 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. 8772
    Prev
    Next
    INDEX
    Explanations

    reel or coil

    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
    å¢ŀå¹ħ
    -0.09
    æĿĪ
    -0.09
    ãģģ
    -0.09
    agne
    -0.09
    ninger
    -0.09
    ting
    -0.08
    ëģĶ
    -0.08
    ники
    -0.08
    odia
    -0.08
    nings
    -0.08
    POSITIVE LOGITS
    ç«¿
    0.11
    ingly
    0.10
    ICAST
    0.10
    ÑĢ
    0.09
    å·©
    0.09
    er
    0.09
    åİŁåĽłæĺ¯
    0.09
    orgh
    0.09
    ä¸ĸ代
    0.09
    ist
    0.08
    Activations Density 0.008%

    No Known Activations