© 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. 63143
    Prev
    Next
    INDEX
    Explanations

    down followed by movement or reduction

    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
    ting
    -0.10
    对ä¸įèµ·
    -0.10
    æ§İ
    -0.10
    çľĭèµ·ä¾Ĩ
    -0.09
    wide
    -0.09
     Redistributions
    -0.09
     Kendall
    -0.09
    IOUS
    -0.09
    iling
    -0.09
    ivity
    -0.09
    POSITIVE LOGITS
    /off
    0.12
    sWith
    0.12
    ä¸ĭæĿ¥çļĦ
    0.10
    ed
    0.10
    kick
    0.10
    ject
    0.09
    /down
    0.09
    pour
    0.09
    -down
    0.09
    hole
    0.09
    Activations Density 0.056%

    No Known Activations