© 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. 56519
    Prev
    Next
    INDEX
    Explanations

    asks for explanation or help

    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
    è¦ģæľī
    -0.10
     ??
    -0.09
    çŁ¥éģĵäºĨ
    -0.09
    å¥ī
    -0.09
    æĪIJè´¥
    -0.08
    -su
    -0.08
     su
    -0.08
    å¾Īæ¸ħæ¥ļ
    -0.08
    belt
    -0.08
    ä¹Łæľīå¾Īå¤ļ
    -0.08
    POSITIVE LOGITS
    ä»ĭç»įä¸Ģä¸ĭ
    0.12
    帮æĪij
    0.11
    è°Īè°Ī
    0.10
    æĮĩçĤ¹
    0.10
    为æĪij们
    0.10
    ä¸Ģä¸ĭ
    0.10
    ä¸Ģè¶Ł
    0.09
    äºĽè®¸
    0.09
    åѦçĶŁä»¬
    0.09
    ä¸Ģ个好çļĦ
    0.09
    Activations Density 0.115%

    No Known Activations