© 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. 21679
    Prev
    Next
    INDEX
    Explanations

    mention of "Hospital"

    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
    ORS
    -0.10
    ä¸Ŀä¸Ŀ
    -0.10
    esti
    -0.09
    stras
    -0.09
    å²ļ
    -0.09
    æŶèĬĤ
    -0.09
    èĩªä¹ł
    -0.09
     ras
    -0.08
    vsp
    -0.08
    ktop
    -0.08
    POSITIVE LOGITS
    éĻ¢éķ¿
    0.09
    åĬ²
    0.08
     ÑĢож
    0.08
     нам
    0.08
    械
    0.08
    åħ±éĿĴ
    0.08
    ä½Ĩä¸įéĻIJäºİ
    0.08
    èĮĥ
    0.08
    åĬłå¿«å»ºè®¾
    0.08
    éĢģæĿ¥
    0.08
    Activations Density 0.030%

    No Known Activations