© 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. 21817
    Prev
    Next
    INDEX
    Explanations

    dates and numbers

    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
    è¿Ļæł·æīįèĥ½
    -0.10
    æĢ§åĴĮ
    -0.10
    æµĻ
    -0.09
    è¿Ļ对äºİ
    -0.09
    æ²³æµģåŁŁ
    -0.09
    çݰ代åĮĸ
    -0.09
    çİ°çĬ¶
    -0.08
    鼷æĸ¯
    -0.08
    ä½Ĩ对äºİ
    -0.08
    äºĨä»ĸçļĦ
    -0.08
    POSITIVE LOGITS
    registr
    0.09
    Ãło
    0.09
    -thirds
    0.09
    animations
    0.08
    contra
    0.08
     تع
    0.08
    /from
    0.08
    aga
    0.08
    .rf
    0.08
    ijke
    0.08
    Activations Density 0.079%

    No Known Activations