© 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. 5761
    Prev
    Next
    INDEX
    Explanations

    doctors and visits

    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
     Cool
    -0.08
    cool
    -0.08
    ibre
    -0.08
     singleton
    -0.08
    _manual
    -0.08
     cool
    -0.08
    å¨ģ
    -0.07
     Baby
    -0.07
     bibli
    -0.07
    hall
    -0.07
    POSITIVE LOGITS
    åĮ»çĶŁ
    0.12
     вÑĢа
    0.11
     visits
    0.11
    éªĮ
    0.10
     Doctors
    0.10
    大夫
    0.10
    é»ĺé»ĺåľ°
    0.10
    åĨħç§ij
    0.10
    Doctors
    0.10
    åIJĿ
    0.10
    Activations Density 0.146%

    No Known Activations