© 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. 31226
    Prev
    Next
    INDEX
    Explanations

    transportation of goods and animals

    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
    笥
    -0.09
    å¼ĵ
    -0.09
    åŀĭåı·
    -0.08
    èĮ¸
    -0.08
    ä¿®å¤į
    -0.08
    æķ·
    -0.08
    çIJħ
    -0.08
    åĪĴ
    -0.08
    åĽĬ
    -0.08
     diver
    -0.08
    POSITIVE LOGITS
    åľºæ¯ĶèµĽ
    0.09
    peq
    0.09
    pson
    0.08
    éļ¾åıĹ
    0.08
    pollo
    0.08
    ÑĪе
    0.08
     Pens
    0.08
    ç¨ļ
    0.08
    Ðĩ
    0.08
     Honor
    0.08
    Activations Density 0.081%

    No Known Activations