© 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. 53516
    Prev
    Next
    INDEX
    Explanations

    harvesting crops

    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
    shopping
    -0.10
    edImage
    -0.09
    éĢĽè¡Ĺ
    -0.09
    å®īå®ļ
    -0.09
    æ½ľ
    -0.08
    ÑĢид
    -0.08
    apro
    -0.08
    è´Ńçī©
    -0.08
    æĺŁå·´
    -0.08
    ä¹ĥæĺ¯
    -0.08
    POSITIVE LOGITS
    æĶ¶èİ·
    0.14
    éĩĩæijĺ
    0.12
    æĶ¶åī²
    0.12
    åĬ³åĬ¨
    0.11
    åĬ³åĬ¨åĬĽ
    0.10
    åŀĽ
    0.10
    æĪIJçĨŁçļĦ
    0.10
     Harvest
    0.10
    丰æĶ¶
    0.10
    æĬ¥éħ¬
    0.10
    Activations Density 0.056%

    No Known Activations