© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 36474
    Prev
    Next
    INDEX
    Explanations

    something 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
    æľīä¸Ģç§į
    -0.09
    ey
    -0.09
    æĺ¯æĪijçļĦ
    -0.08
    -0.08
    äºĭå®ľ
    -0.08
     sorts
    -0.08
    äºĨå¤ļå°ij
    -0.08
    äºĮåŃĹ
    -0.08
    aldi
    -0.08
    uming
    -0.08
    POSITIVE LOGITS
    à¹Ģà¸Ħ
    0.12
    à®´
    0.10
    æĢ»èĢĮè¨Ģä¹ĭ
    0.10
    èģĮä¸ļçĶŁæ¶¯
    0.09
    æĢ»ä¹ĭ
    0.09
    å¥
    0.09
    åIJIJ
    0.09
    ines
    0.09
    labs
    0.09
    åļ¼
    0.09
    Activations Density 0.085%

    No Known Activations