© 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. 55934
    Prev
    Next
    INDEX
    Explanations

    names of people called Shapiro

    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
    ivent
    -0.09
    è¿Ļæĸ¹éĿ¢
    -0.09
    ÑIJ
    -0.08
    /*.
    -0.08
    ITS
    -0.08
    itter
    -0.08
     Premier
    -0.08
    records
    -0.08
     Mah
    -0.08
     records
    -0.08
    POSITIVE LOGITS
    çģ°èī²
    0.09
    holm
    0.09
    ackle
    0.09
     dao
    0.09
     Dao
    0.08
    .Counter
    0.08
    _supply
    0.08
    ROUGH
    0.08
    _WRAPPER
    0.08
    岸
    0.08
    Activations Density 0.019%

    No Known Activations