© 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. 18221
    Prev
    Next
    INDEX
    Explanations

    eating and drinking

    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
    å¡ŀ
    -0.09
    обоÑĢ
    -0.08
     Det
    -0.08
    å±ħ
    -0.08
    ç«Ļåľ¨
    -0.08
    åĨķ
    -0.08
    æł´
    -0.08
    LAND
    -0.08
    åĪ¶
    -0.08
    å»īä»·
    -0.08
    POSITIVE LOGITS
    íĥĦ
    0.10
    è´»
    0.10
    å¾Ĺ罪
    0.10
    ä¹±
    0.09
    ager
    0.09
    åĮĸè¿Ľç¨ĭ
    0.09
    å¼ĭ
    0.09
    agan
    0.09
    å§Ķç»Ħç»ĩ
    0.09
    亨
    0.09
    Activations Density 0.031%

    No Known Activations