© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37516
    Prev
    Next
    INDEX
    Explanations

    acupuncture practice

    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
    ä¸Ńåħ³
    -0.10
    ose
    -0.09
    ợ
    -0.08
    çı°
    -0.08
    fos
    -0.08
    ä¼ĺè´¨çļĦ
    -0.08
    PASS
    -0.07
    osal
    -0.07
    isha
    -0.07
    rets
    -0.07
    POSITIVE LOGITS
     needles
    0.09
    .Designer
    0.09
    ç²²
    0.09
    麻çĹ¹
    0.09
    .Pin
    0.09
    ystems
    0.09
    è¿Ľåıĸ
    0.09
     Ngh
    0.09
    èĬĴ
    0.09
     Honor
    0.09
    Activations Density 0.005%

    No Known Activations