© 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. 9118
    Prev
    Next
    INDEX
    Explanations

    parts of the body

    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
    æĬļæij¸
    -0.09
    顺
    -0.08
    æĥ©ç½ļ
    -0.08
    older
    -0.08
    èģļ
    -0.08
    çĤķ
    -0.08
    bote
    -0.08
    ç§ķ
    -0.08
    ç«Ń
    -0.08
    äºĮç»´
    -0.08
    POSITIVE LOGITS
     пÑĢÑı
    0.09
    ubs
    0.09
    客è§Ĥ
    0.09
    èµĸ以
    0.09
    åĨħéĺģ
    0.09
    ä¸įå®ľ
    0.09
    owi
    0.09
    ç´§æī£
    0.08
    ä¸įéĶĻ
    0.08
    æĮºå¥½
    0.08
    Activations Density 0.137%

    No Known Activations