© 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. 26453
    Prev
    Next
    INDEX
    Explanations

    their use, they use

    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
    ç»ĥ
    -0.10
    ataka
    -0.10
    åĴ±
    -0.09
     OUR
    -0.09
    第äºĮ大
    -0.09
    æĪijä»¬ä¹Ł
    -0.08
    æĪij们çļĦ
    -0.08
    åĴ±ä»¬
    -0.08
    åĬ¨æijĩ
    -0.08
    ather
    -0.08
    POSITIVE LOGITS
    åijĬè¯īä»ĸ
    0.14
    åijĬè¯ī她
    0.12
    让ä»ĸ
    0.11
     him
    0.10
    å·¥
    0.10
    è¿Ļä½į
    0.10
    æĺ¯ä»ĸ
    0.10
    ç»Ļä»ĸ
    0.10
    帮ä»ĸ
    0.10
    她
    0.10
    Activations Density 0.152%

    No Known Activations