© 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. 61204
    Prev
    Next
    INDEX
    Explanations

    accomplish, achieve, get things done

    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
    ä¼ģä¸ļæıIJä¾Ľ
    -0.10
    merc
    -0.09
    离å¼ĢäºĨ
    -0.09
    çľģåħ¬å®īåİħ
    -0.09
    禾
    -0.09
    æ³ķå¾ĭ责任
    -0.09
    æīĭå·¥
    -0.09
    èĭĶ
    -0.09
    ongan
    -0.09
    åŀĽ
    -0.09
    POSITIVE LOGITS
    åģļäºĭ
    0.12
    å®ŀå¹²
    0.10
    æݨåĬ¨
    0.10
    è¡ĮåĬ¨
    0.10
    åĬŀäºĭ
    0.10
    åĬŀå®ŀäºĭ
    0.09
    åĩºå·®
    0.09
    äºĭæĥħ
    0.09
    Authorization
    0.09
     action
    0.09
    Activations Density 0.043%

    No Known Activations