© 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. 52924
    Prev
    Next
    INDEX
    Explanations

    hormone and hormones

    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
    èŀįåIJĪåıijå±ķ
    -0.09
    èŀįåĮĸ
    -0.09
    æµ·éĩı
    -0.09
    endar
    -0.09
    åIJ¸æĶ¶
    -0.09
    çķĮ
    -0.09
    夹
    -0.09
    erview
    -0.09
    Ñī
    -0.09
    æłĬ
    -0.09
    POSITIVE LOGITS
     hormones
    0.12
    æ¿Ģç´ł
    0.10
     hormone
    0.09
    åĤ¬
    0.09
    æ»ŀ
    0.08
    æ¾į
    0.08
    æĬij
    0.08
    çĶĺ
    0.08
    ä¿ĥ
    0.08
    åĸ·
    0.08
    Activations Density 0.300%

    No Known Activations