© 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. 2418
    Prev
    Next
    INDEX
    Explanations

    follow these steps

    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
    èIJ½ä¸ĭ
    -0.10
    åŃIJå¼Ł
    -0.10
    åIJĥä»Ģä¹Ī
    -0.10
    ål
    -0.09
    å½¢
    -0.09
    åĵªåĦ¿
    -0.09
    碰
    -0.09
    åĴ¬
    -0.09
    å¤ĩæ¡Ī
    -0.09
    éĴ¤
    -0.09
    POSITIVE LOGITS
    æĮĩå¼ķ
    0.11
     instructions
    0.09
    _steps
    0.09
     steps
    0.09
    ä¸ĢæŃ¥æŃ¥
    0.08
    级以ä¸Ĭ
    0.08
    æŃ¥éª¤
    0.08
    _cu
    0.08
    operands
    0.08
    .proc
    0.08
    Activations Density 0.035%

    No Known Activations