© 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. 57164
    Prev
    Next
    INDEX
    Explanations

    prior art

    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
    é©´
    -0.10
    åĪ°åºķ
    -0.09
    ä¸ŀ
    -0.09
    æľīåIJį
    -0.09
    ç²¾è£ħ
    -0.09
    è°£
    -0.09
    å¤ĩ
    -0.09
    èĥĮåIJİ
    -0.09
    ä¸İä¼Ĺä¸įåIJĮ
    -0.09
    åĪ°åºķæĺ¯
    -0.09
    POSITIVE LOGITS
    ä¸ļåĨħ
    0.09
    ç¨Ķ
    0.09
    _baseline
    0.08
    çĨŁçŁ¥
    0.08
    è¦ģåģļ好
    0.08
    Baseline
    0.08
    æĬĢæľ¯æ°´å¹³
    0.08
    ring
    0.08
    æĥ³åĪ°äºĨ
    0.08
    edges
    0.08
    Activations Density 0.422%

    No Known Activations