© 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. 23097
    Prev
    Next
    INDEX
    Explanations

    compared with

    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
    举äºļ
    -0.10
    dz
    -0.08
    éĹªèĢĢ
    -0.08
    FLASH
    -0.08
    ä¾®
    -0.08
    lte
    -0.08
    éĴµ
    -0.08
    Runner
    -0.08
    éħįåIJĪ
    -0.08
    iao
    -0.07
    POSITIVE LOGITS
    åĵªåĦ¿
    0.09
    娣
    0.09
    toMatchSnapshot
    0.09
    ç£ħ
    0.09
    è¡°éĢĢ
    0.09
    isposable
    0.09
     Bek
    0.09
    æĦıä¹īä¸ĬçļĦ
    0.08
    ä¸ĢåĪĩéĥ½
    0.08
    èģĮä¸ļ
    0.08
    Activations Density 0.703%

    No Known Activations