© 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. 10268
    Prev
    Next
    INDEX
    Explanations

    water and hydration

    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
    ä¸Ģæŀļ
    -0.10
    stm
    -0.09
    ạ
    -0.09
    ç¿ĺ
    -0.09
    -tested
    -0.09
    寮
    -0.09
    .then
    -0.09
    unal
    -0.08
    æĸĻ
    -0.08
    éĩįç»Ħ
    -0.08
    POSITIVE LOGITS
    åĸĿæ°´
    0.10
    æ±Ĺ
    0.10
    uri
    0.10
    åĩºæ±Ĺ
    0.09
    æ¯ı天éĥ½
    0.08
    enser
    0.08
    irs
    0.08
    æľīä»·åĢ¼
    0.08
    lland
    0.08
    å·¥ç¨ĭæĸ½å·¥
    0.08
    Activations Density 0.023%

    No Known Activations