© 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. 27228
    Prev
    Next
    INDEX
    Explanations

    all the

    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
    epar
    -0.09
    ç§ī
    -0.09
    çĴŀ
    -0.08
    éĢĭ
    -0.08
    åľ¨åIJĮä¸Ģ
    -0.08
     gdy
    -0.08
    drv
    -0.08
    èıľ
    -0.08
     extinction
    -0.08
    åľĴ
    -0.08
    POSITIVE LOGITS
    çļĦä¿¡å¿ĥ
    0.10
    æĪIJçĨŁçļĦ
    0.09
    çľĭæ¸ħ
    0.09
    讳
    0.09
    çĦľ
    0.09
    èģĮæĿĥ
    0.09
    æĸĹå¿Ĺ
    0.08
    _VEC
    0.08
    çļĦ帮åĬ©ä¸ĭ
    0.08
    æľ
    0.08
    Activations Density 0.017%

    No Known Activations