© 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. 2706
    Prev
    Next
    INDEX
    Explanations

    numbers, percentages, and quantities

    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
    ä¸įä½Ĩ
    -0.12
    ä¸įåĥħ
    -0.10
    ä¸įä»ħ
    -0.10
    åģļçļĦäºĭæĥħ
    -0.10
    çIJĨ解åĴĮ
    -0.09
     both
    -0.09
     zarówno
    -0.09
    erved
    -0.09
    管çIJĨåĴĮ
    -0.09
    åħ¨éķĩ
    -0.09
    POSITIVE LOGITS
    /or
    0.13
    /OR
    0.10
    venge
    0.10
    åº
    0.09
    缸åºĶçļĦ
    0.09
    bone
    0.09
    _SS
    0.09
    ç¼Ł
    0.09
    idue
    0.09
    å¾Ī强
    0.09
    Activations Density 0.223%

    No Known Activations