© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 62823
    Prev
    Next
    INDEX
    Explanations

    strategies and initiatives

    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
    uste
    -0.12
    æıį
    -0.09
    ilst
    -0.08
     Anat
    -0.08
    ude
    -0.08
     unofficial
    -0.08
    æĭĩ
    -0.08
    è¥Ł
    -0.08
    çļĦæĦŁåıĹ
    -0.08
    鸽
    -0.08
    POSITIVE LOGITS
    æĪĹ
    0.09
    ç»ĵ
    0.09
    IPH
    0.09
    antha
    0.09
    .FLAG
    0.09
    é©Ń
    0.09
    纲
    0.09
    erness
    0.08
    èĮĥ
    0.08
    被æī§è¡Į
    0.08
    Activations Density 0.092%

    No Known Activations