© 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. 55187
    Prev
    Next
    INDEX
    Explanations

    hospital or medical treatment

    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
    ä½łèĩªå·±
    -0.10
    æıIJåīį
    -0.09
    å½±åĵįåĬĽçļĦ
    -0.08
    æıIJæĹ©
    -0.08
    æ¶ķ
    -0.08
     Ðijез
    -0.08
    çű
    -0.08
    .foundation
    -0.08
    amil
    -0.07
     cripp
    -0.07
    POSITIVE LOGITS
    reu
    0.10
    éĵ
    0.09
    è¿ŀå¤ľ
    0.09
    çŁŃæŶéĹ´åĨħ
    0.09
    æĺİæĹ¥
    0.09
    å¤©åĽ½
    0.09
     spiked
    0.09
    åij¨åĽĽ
    0.09
     dù
    0.08
    åij¨æģ©
    0.08
    Activations Density 0.054%

    No Known Activations