© 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. 61511
    Prev
    Next
    INDEX
    Explanations

    would have

    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
    åĵ²
    -0.10
    åıĪ好
    -0.10
    临
    -0.10
    æ·ĭ
    -0.09
     Leon
    -0.09
    ä¸ĢçĶŁ
    -0.08
    æĶ¾ä¸ĭ
    -0.08
    ãģ§ãģĹãĤĩãģĨãģŃ
    -0.08
    å¥ĸ
    -0.08
    对çĿĢ
    -0.08
    POSITIVE LOGITS
    å¦Ĥæŀľä¸įæĺ¯
    0.16
    å¦Ĥæŀľæ²¡æľī
    0.16
    å°±ä¸įä¼ļ
    0.10
     wouldn
    0.10
    åIJ¦åĪĻ
    0.09
    é¢ĦåijĬ
    0.09
     nếu
    0.09
    è¦ģæĺ¯
    0.09
    IfNeeded
    0.09
    æĪ¿ä¸ľ
    0.09
    Activations Density 0.051%

    No Known Activations