© 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. 49996
    Prev
    Next
    INDEX
    Explanations

    physical therapy and rehabilitation

    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
    æĻ¯å¾·
    -0.09
    ä¹IJæĦı
    -0.09
    å±ıèĶ½
    -0.09
    å£ģ
    -0.09
    æĤĸ
    -0.09
    hal
    -0.09
    æĮł
    -0.08
    å®°
    -0.08
    formation
    -0.08
     дог
    -0.08
    POSITIVE LOGITS
    therapy
    0.11
    çīµå¼ķ
    0.10
     therapy
    0.10
    çĻĤ
    0.10
    æķ·
    0.09
     therapists
    0.09
     Alphabet
    0.09
    èIJģ
    0.09
    otherapy
    0.09
    说è¯Ŀ
    0.09
    Activations Density 0.096%

    No Known Activations