© 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. 10119
    Prev
    Next
    INDEX
    Explanations

    don't have to worry

    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
    omat
    -0.10
    è¿Ļç§įæĥħåĨµ
    -0.10
    _less
    -0.09
    onte
    -0.09
    icket
    -0.09
    è¦ģçĶ¨
    -0.09
    ä¸įåıĬ
    -0.09
    æŀ¶
    -0.09
    ä¾ĥ
    -0.08
    ä¸įæŃ»
    -0.08
    POSITIVE LOGITS
    ä»»ä½ķ
    0.16
    æľīä»»ä½ķ
    0.15
    æĢĿèĢĥ
    0.13
    çIJĨä¼ļ
    0.12
    èĢĥèĻij
    0.12
    æĭħå¿ĥ
    0.12
     any
    0.11
    Anything
    0.11
     anything
    0.11
    æĭħ忧
    0.11
    Activations Density 0.029%

    No Known Activations