© 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. 50263
    Prev
    Next
    INDEX
    Explanations

    hospital or facility

    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¸ĢéŨ
    -0.09
    ç«
    -0.09
    _dashboard
    -0.08
     toggle
    -0.08
    å®°
    -0.08
    avit
    -0.08
    kest
    -0.08
    hta
    -0.08
    _SUITE
    -0.08
    åĵģè´¨
    -0.08
    POSITIVE LOGITS
     facility
    0.12
    etten
    0.10
    facility
    0.10
     facilities
    0.10
    èĩ´åĬĽ
    0.10
    强åĪ¶
    0.10
    设æĸ½
    0.09
    æľºæŀĦ
    0.09
     Went
    0.09
    äºĨå¤ļå°ij
    0.09
    Activations Density 0.103%

    No Known Activations