© 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. 5652
    Prev
    Next
    INDEX
    Explanations

    competition or team events

    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
    åĪĨæµģ
    -0.08
    èµ·ä¾Ĩ
    -0.08
    红楼
    -0.08
    .sg
    -0.08
    stre
    -0.07
    mise
    -0.07
    atum
    -0.07
    uppe
    -0.07
    æ¸į
    -0.07
     boyfriend
    -0.07
    POSITIVE LOGITS
    å¸ļ
    0.10
    gli
    0.10
    ares
    0.10
    forth
    0.10
    aring
    0.10
    że
    0.10
    VES
    0.09
    å¾ĢåIJİ
    0.09
    zelf
    0.09
    izar
    0.09
    Activations Density 0.293%

    No Known Activations