© 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. 4843
    Prev
    Next
    INDEX
    Explanations

    UI controls like scroll, keyboard, and screen

    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
    ç³»
    -0.10
    æķ²
    -0.09
     Android
    -0.09
     princ
    -0.08
    /android
    -0.08
    Android
    -0.08
    èĵ¼
    -0.08
    .Android
    -0.08
    android
    -0.08
     android
    -0.08
    POSITIVE LOGITS
    æIJª
    0.10
    ä¸įä¿¡
    0.09
    çĩ®
    0.09
    stantiate
    0.09
    ónica
    0.09
    ä¸Ģåı°
    0.09
    çıī
    0.08
    rvine
    0.08
     Seeder
    0.08
    åŁŁ
    0.08
    Activations Density 0.278%

    No Known Activations