© 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. 53424
    Prev
    Next
    INDEX
    Explanations

    pregnant women and pregnancy

    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
    被人
    -0.09
    è¿İæİ¥
    -0.09
    å¢ŀè¿Ľ
    -0.09
    æĹ»
    -0.09
    èĵĿ天
    -0.08
    èµ·äºĨ
    -0.08
    æīįä¼ļ
    -0.08
    ä¾£
    -0.08
    rem
    -0.08
    è¡Ĺ
    -0.08
    POSITIVE LOGITS
    lake
    0.10
    aths
    0.09
    泺
    0.09
    åĭ¿
    0.09
     CharSequence
    0.09
    éĻ¤éĿŀ
    0.09
    å°¤
    0.09
    uetype
    0.09
    æħİ
    0.08
    .isPresent
    0.08
    Activations Density 0.043%

    No Known Activations