© 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. 55274
    Prev
    Next
    INDEX
    Explanations

    author or authors

    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
    çħ§æł·
    -0.09
    é¢ĩ
    -0.08
    æĿ¯
    -0.08
    赢家
    -0.08
     Pics
    -0.08
    åIJ¦
    -0.08
     á»ķ
    -0.08
    zing
    -0.08
    ilder
    -0.08
     Cotton
    -0.07
    POSITIVE LOGITS
    äºĭå®ŀ
    0.10
    elly
    0.10
    èµIJ
    0.09
     Sho
    0.09
    éģµ
    0.09
    uffs
    0.08
    éģĩéļ¾
    0.08
    rist
    0.08
    apt
    0.08
    ordo
    0.08
    Activations Density 0.003%

    No Known Activations