© 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. 4448
    Prev
    Next
    INDEX
    Explanations

    hospital and health system names

    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
     Zy
    -0.10
    æ··
    -0.08
    ISTER
    -0.08
    大åݦ
    -0.08
    æīª
    -0.08
     zw
    -0.08
     bl
    -0.08
     Sunday
    -0.07
     rever
    -0.07
    ertz
    -0.07
    POSITIVE LOGITS
    åijµæĬ¤
    0.11
    æľĢåħĪ
    0.09
    第ä¸Ģ家
    0.09
    isos
    0.09
     Overse
    0.09
    æģ
    0.09
    /favicon
    0.09
    æŀĭ
    0.09
    æłİ
    0.09
    åĮ»éĻ¢
    0.09
    Activations Density 0.053%

    No Known Activations