© 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. 30505
    Prev
    Next
    INDEX
    Explanations

    gene flow, dispersal, restoration, landscape

    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
    china
    -0.11
    uala
    -0.10
    å·¥ä¸ļ
    -0.10
     stalls
    -0.09
    angs
    -0.09
    RIPT
    -0.09
    zia
    -0.09
    èĢĻ
    -0.09
     Yates
    -0.09
    åı¯ä»¥çĽ´æİ¥
    -0.09
    POSITIVE LOGITS
     Moff
    0.09
    imal
    0.09
    3
    0.08
    6
    0.08
     Curt
    0.08
    bil
    0.08
     bil
    0.08
    4
    0.08
    1
    0.08
    åIJĮåŁİ
    0.08
    Activations Density 0.092%

    No Known Activations