© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21726
    Prev
    Next
    INDEX
    Explanations

    university and location names

    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
    .Ui
    -0.09
     bleed
    -0.09
    åĬ¨å·¥
    -0.09
    иж
    -0.08
    é»İæĺİ
    -0.08
    åIJĦåİ¿
    -0.08
    åį«è§Ĩ
    -0.08
    ball
    -0.08
    ìŀ¥ìĿĦ
    -0.08
    adar
    -0.07
    POSITIVE LOGITS
    å¡«è¡¥
    0.10
    伦æķ¦
    0.10
     Hat
    0.10
    ç¬ĭ
    0.09
    顶
    0.09
    人çī©
    0.09
    åľ¨åĵª
    0.09
    isz
    0.09
    婵
    0.08
    firm
    0.08
    Activations Density 0.034%

    No Known Activations