© 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. 22198
    Prev
    Next
    INDEX
    Explanations

    combine, divide, apply

    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
    .openg
    -0.08
    èĬĹ
    -0.08
    way
    -0.08
    ç«ĭ
    -0.08
    ward
    -0.08
    åħ¥åı£
    -0.08
     sacrifices
    -0.08
     Unity
    -0.07
    ieri
    -0.07
    å©Ĩ
    -0.07
    POSITIVE LOGITS
    æľīèĥ½åĬĽ
    0.10
    çļ±
    0.10
    olin
    0.10
    æѤç§į
    0.09
    éģĩä¸Ĭ
    0.09
    å¾ĭå¸ĪäºĭåĬ¡
    0.09
    èµ·ä¾Ĩ
    0.09
    è¿Ļå¥Ĺ
    0.09
    ç§įç§į
    0.09
    åĬłä¸Ĭ
    0.09
    Activations Density 0.118%

    No Known Activations