© 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. 47827
    Prev
    Next
    INDEX
    Explanations

    via followed by a modality

    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
    /or
    -0.13
    alus
    -0.10
    мен
    -0.10
    yna
    -0.09
    é«®
    -0.09
    wick
    -0.09
    nt
    -0.09
    si
    -0.09
    ×ķת
    -0.09
    ãģªãĤĬ
    -0.09
    POSITIVE LOGITS
    èĩ¾
    0.11
    ogh
    0.11
    åįķä¸Ģ
    0.10
    åħ¶æīĢ
    0.10
    å°ıäºĭ
    0.10
    èĩªçĦ¶èĢĮ
    0.10
    ãĢħ
    0.09
    ç²¼
    0.09
    ä¸įåIJĮçļĦ
    0.08
    建设åĴĮ
    0.08
    Activations Density 0.032%

    No Known Activations