© 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. 9008
    Prev
    Next
    INDEX
    Explanations

    Crystal Reports, bowling, score

    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
    对æĸ¹
    -0.10
    è¡ħ
    -0.10
    æĬĽå¼ĥ
    -0.09
    åĬ²
    -0.09
    åĢį
    -0.09
    зам
    -0.09
    ê°ģ
    -0.09
    åĩij
    -0.09
    agem
    -0.09
    ç¥Ŀç¦ı
    -0.08
    POSITIVE LOGITS
    梳
    0.10
    -May
    0.09
    ideos
    0.09
    æĮģ
    0.08
    .jboss
    0.08
     Garn
    0.08
    reon
    0.08
    Porn
    0.08
     gol
    0.08
     bow
    0.08
    Activations Density 0.104%

    No Known Activations