© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51977
    Prev
    Next
    INDEX
    Explanations

    moon surface communications equipment

    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
    赶æĿ¥
    -0.10
    ä¸ĬéŨ
    -0.09
    çĵľ
    -0.09
    åĩ°
    -0.08
    æ»¨æ±Ł
    -0.08
    æĮĩåįĹ
    -0.08
     aqu
    -0.08
    æĵ¤
    -0.08
    éĴ¥åĮĻ
    -0.08
    _CONF
    -0.08
    POSITIVE LOGITS
    åĿ¡
    0.11
    èĶĵ
    0.10
    嫦
    0.09
    æĪĴ
    0.09
    ä¸įåĪ°
    0.09
    èĮĨ
    0.08
    ноп
    0.08
    é«ĺå°Ķ夫
    0.08
    å¨ĥ
    0.08
    ustin
    0.08
    Activations Density 0.029%

    No Known Activations