© 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. 5115
    Prev
    Next
    INDEX
    Explanations

    numbers and approximations

    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
    æľĢæĹ©
    -0.10
    æĦīå¿«
    -0.10
    æģ°
    -0.09
    åIJĮæł·çļĦ
    -0.09
    åĩºçĤī
    -0.09
    å¾Īéĩįè¦ģçļĦ
    -0.09
    èĭĮ
    -0.09
    æĬĦ
    -0.09
     Cyrus
    -0.09
     zwar
    -0.09
    POSITIVE LOGITS
    æľīä»»ä½ķ
    0.10
    UIL
    0.10
    èĤ©
    0.09
    ä¹Łä¸įè¦ģ
    0.09
    åŁºæľ¬
    0.08
    å°¤åħ¶æĺ¯
    0.08
    bur
    0.08
    esp
    0.08
     anything
    0.08
    就没æľī
    0.08
    Activations Density 0.171%

    No Known Activations