© 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. 4983
    Prev
    Next
    INDEX
    Explanations

    greatest people, efficient filtration systems

    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
     именно
    -0.10
    aret
    -0.09
    ONS
    -0.08
    æľīæĿ¡ä»¶
    -0.08
    æģ°å¥½
    -0.08
    åĪļ好
    -0.08
    ForRow
    -0.08
    ä¸įåıªæĺ¯
    -0.08
    UpDown
    -0.08
    hole
    -0.08
    POSITIVE LOGITS
    åĨįå¤ļ
    0.17
    æľīå¤ļä¹Ī
    0.13
    æľīå¤ļ大
    0.12
    ä¹Łä¸įåı¯èĥ½
    0.12
    ãģĹãģ¦ãĤĤ
    0.11
    å¤ļä¹Ī
    0.11
     fancy
    0.11
    ä¹ŁæĹłæ³ķ
    0.11
     mãi
    0.10
    趸
    0.10
    Activations Density 0.042%

    No Known Activations