© 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. 7414
    Prev
    Next
    INDEX
    Explanations

    weaning / lactating / suckling

    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
    .wrapper
    -0.09
    å¡ŀ
    -0.09
    åħ¨ç¨ĭ
    -0.09
    è¿Ļæł·è¯´
    -0.09
    dera
    -0.08
    udder
    -0.08
    ä¾ĥ
    -0.08
     hops
    -0.08
    åħĨ
    -0.08
    borough
    -0.08
    POSITIVE LOGITS
    å¾®éĩı
    0.08
     latch
    0.08
    å½Ń
    0.08
    å½¹
    0.08
    .appspot
    0.08
    abras
    0.08
    è¾IJ
    0.08
    à¸Ĺาà¸ĩ
    0.08
    oret
    0.08
    .compat
    0.08
    Activations Density 0.188%

    No Known Activations