© 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. 53717
    Prev
    Next
    INDEX
    Explanations

    prescribing medication

    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
    çī¹
    -0.09
    èľ»
    -0.08
    pery
    -0.08
    èī¦
    -0.08
     Om
    -0.08
    顺便
    -0.08
    worm
    -0.08
    åIJ¸æĶ¶
    -0.08
     trilogy
    -0.07
    ç»ĪçĤ¹
    -0.07
    POSITIVE LOGITS
    å¤Ħæĸ¹
    0.13
    å¼Ģåħ·
    0.12
    å¼Ģåĩº
    0.12
    髯
    0.12
    æĬĹçĶŁç´ł
    0.11
     prescribe
    0.11
    åIJĪçIJĨ
    0.11
    æĬĹæĪĺ
    0.11
     prescriptions
    0.10
     prescription
    0.10
    Activations Density 0.152%

    No Known Activations