© 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. 23882
    Prev
    Next
    INDEX
    Explanations

    horticulture and agriculture

    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
    nable
    -0.09
    nings
    -0.09
    è¢ħ
    -0.09
     makers
    -0.08
    æŶ任
    -0.08
    è¢Ń
    -0.08
    ÑĩÑĥ
    -0.08
     ÐĴаÑģ
    -0.08
    羣å®ŀ
    -0.08
     Hogan
    -0.08
    POSITIVE LOGITS
    åĽŃ
    0.11
    urally
    0.10
    iculture
    0.10
    ists
    0.10
    icultural
    0.09
    -ag
    0.09
    äºĶçĻ¾
    0.09
    é¾Ħ
    0.09
    ศาส
    0.09
    iras
    0.08
    Activations Density 0.014%

    No Known Activations