© 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. 1065
    Prev
    Next
    INDEX
    Explanations

    fat

    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
    棣
    -0.09
    éªŀ
    -0.09
    Fade
    -0.09
    缴éĶĢ
    -0.09
     Gentle
    -0.08
    é²ľ
    -0.08
    åħ¥
    -0.08
    ä»Ģä¹Īäºĭæĥħ
    -0.08
    money
    -0.08
    æİĢ
    -0.08
    POSITIVE LOGITS
    èĦĤèĤª
    0.11
    åłĨ积
    0.10
    èĤª
    0.09
    éĤ£ä¸ªäºº
    0.09
    çĭ¡
    0.09
    éķĩæĶ¿åºľ
    0.09
    бав
    0.09
    åĬŀäºĭå¤Ħ
    0.09
    æ²¹èħ»
    0.09
     Fat
    0.08
    Activations Density 0.079%

    No Known Activations