© 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. 8040
    Prev
    Next
    INDEX
    Explanations

    bedside manner and communication strategies

    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¸įåIJĪçIJĨ
    -0.09
    ä¼Ļ
    -0.09
    สà¸Ļ
    -0.09
    åĿļ
    -0.08
     Chall
    -0.08
     اÙĦÙħÙĨ
    -0.08
    alic
    -0.08
    _fault
    -0.08
    çĶ¨åĵģ
    -0.08
    æ´¾éģ£
    -0.08
    POSITIVE LOGITS
    人æĢ§åĮĸ
    0.12
    人æĸĩ
    0.11
    æ²ŁéĢļ
    0.11
    ãĤ³ãĥŁãĥ¥ãĥĭãĤ±ãĥ¼ãĤ·ãĥ§ãĥ³
    0.11
    çĸı导
    0.10
    ç»Ĩèħ»
    0.10
    è´´å¿ĥ
    0.10
    åĬłçĽŁåºĹ
    0.10
    ĥģ
    0.10
    åīįåı°
    0.10
    Activations Density 0.093%

    No Known Activations