© 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. 32863
    Prev
    Next
    INDEX
    Explanations

    vegetable cultivation and breeding

    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
    ©
    -0.10
    usz
    -0.10
    ned
    -0.10
    ãģ£ãģįãĤĬ
    -0.09
    رس
    -0.09
     itemprop
    -0.09
    nable
    -0.09
     Serg
    -0.09
    ยา
    -0.08
     Apartment
    -0.08
    POSITIVE LOGITS
    aled
    0.11
    çİĭåĽ½
    0.10
    aters
    0.09
    tte
    0.09
    stalk
    0.09
    sWith
    0.09
    ðŁ¥ķ
    0.09
    asted
    0.09
     Bri
    0.08
    大æ£ļ
    0.08
    Activations Density 0.013%

    No Known Activations