© 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. 18429
    Prev
    Next
    INDEX
    Explanations

    this followed by context

    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¸ı
    -0.09
    åįĹæ²Ļ
    -0.09
    秣
    -0.09
    åij¼
    -0.09
    urt
    -0.09
     ÑĤомÑĥ
    -0.09
    å°º
    -0.08
    lix
    -0.08
     Ctrl
    -0.08
    ëij¥
    -0.08
    POSITIVE LOGITS
    /out
    0.11
     regard
    0.10
    亹
    0.09
    æł¸åĩĨ
    0.09
    æĥħ趣
    0.09
    潺
    0.08
    å±ĭåŃIJ
    0.08
    éĢĤå®ľ
    0.08
    说ä»Ģä¹Ī
    0.08
    è¿ĺæĺ¯æ¯Ķè¾ĥ
    0.08
    Activations Density 0.075%

    No Known Activations