© 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. 52037
    Prev
    Next
    INDEX
    Explanations

    manifest.json or other manifest files

    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
    媳
    -0.10
    brush
    -0.09
    isplay
    -0.09
    ods
    -0.09
    outs
    -0.09
    itch
    -0.09
     Compact
    -0.08
    åıijå±ķ壮大
    -0.08
    ç§ijåѦéĻ¢
    -0.08
    idge
    -0.08
    POSITIVE LOGITS
    edly
    0.12
    ations
    0.12
    ively
    0.12
    ually
    0.11
    ly
    0.10
    ments
    0.10
    ment
    0.10
    oes
    0.10
    äºĨ个
    0.09
    äºĨèĩªå·±çļĦ
    0.09
    Activations Density 0.025%

    No Known Activations