© 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. 61058
    Prev
    Next
    INDEX
    Explanations

    vomiting and sickness

    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
    Miller
    -0.09
    çĹ´
    -0.09
    é¢ĩ
    -0.09
     Wilmington
    -0.08
    éc
    -0.08
    æľĪä¸ĭ
    -0.08
    elier
    -0.08
    ãģĹãģ°
    -0.08
    ç¿ģ
    -0.08
     нек
    -0.08
    POSITIVE LOGITS
    åijķåIJIJ
    0.11
    å³Ĵ
    0.10
    ores
    0.10
    è§Ħéģ¿
    0.09
    èļ±
    0.09
    ç¦ıåĪ©
    0.09
    å·´æĭī
    0.08
    åĴİ
    0.08
    ä¹ĭä½Ļ
    0.08
     Hem
    0.08
    Activations Density 0.013%

    No Known Activations