© 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. 62996
    Prev
    Next
    INDEX
    Explanations

    again, further, finally

    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¿Ļä¹Ī说
    -0.12
    å½ĵåĪĿ
    -0.11
    å°±è¿Ļä¹Ī
    -0.11
    æĺ¯å¤ļä¹Ī
    -0.10
    éļ¾æĢª
    -0.10
    ãģĹãģŁãģĵãģ¨
    -0.10
    就已ç»ı
    -0.09
    è¿Ļæł·è¯´
    -0.09
    ç²ij
    -0.09
    涤
    -0.09
    POSITIVE LOGITS
    åĨį次
    0.17
    åĨįä¸Ģ次
    0.13
    again
    0.12
     again
    0.12
    æľĢåIJİ
    0.11
    åĨį度
    0.11
     further
    0.11
    è¿Ľä¸ĢæŃ¥
    0.11
    Finally
    0.10
     Again
    0.10
    Activations Density 0.010%

    No Known Activations