© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 19343
    Prev
    Next
    INDEX
    Explanations

    farming, January, fairtrade

    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
    .Automation
    -0.10
    åIJĮåŁİ
    -0.10
    ARC
    -0.09
    å®īå®ļ
    -0.09
    é«ĺéĵģ
    -0.09
    æķĪåĬĽ
    -0.09
    -library
    -0.09
    (lib
    -0.09
     Inn
    -0.08
    åľ¨æł¡
    -0.08
    POSITIVE LOGITS
    åĽŃ
    0.12
    wise
    0.09
    åľĴ
    0.09
    åİŁæĸĻ
    0.09
    åľĨ
    0.09
    åĬ³
    0.08
    èµ·æºIJ
    0.08
     Dump
    0.08
    çĶŁéķ¿
    0.08
    çĿ«æ¯Ľ
    0.08
    Activations Density 0.096%

    No Known Activations