© 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. 5813
    Prev
    Next
    INDEX
    Explanations

    birth and related medical terms

    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
    ายà¸Ļ
    -0.09
    å°ij女
    -0.09
    ä¼ĺè¶Ĭ
    -0.09
    ê°ij
    -0.09
    æĢĤ
    -0.08
    让èĩªå·±
    -0.08
    æĤłæĤł
    -0.08
    æĢĢåŃķ
    -0.08
    _APPEND
    -0.08
    åij¨å¹´
    -0.08
    POSITIVE LOGITS
    å½ĵæĻļ
    0.11
    åĮĹ京æŶéĹ´
    0.11
    æݥ管
    0.11
    åįĬ个å°ıæŶ
    0.10
    åįĬå°ıæŶ
    0.10
    å½ĵ天
    0.09
    /operators
    0.09
    eln
    0.09
    ç«ĭåĪ»
    0.09
     ê²
    0.09
    Activations Density 0.063%

    No Known Activations