© 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. 51188
    Prev
    Next
    INDEX
    Explanations

    crowdsourcing, crowdfunding, vote, community, collection

    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
    ä»ĺ
    -0.09
    éĿĵ
    -0.09
    å¯Įæ°ij
    -0.08
    (OP
    -0.08
    æĪ¿åŃIJ
    -0.08
    å±¥èģĮ
    -0.08
    èī¯
    -0.08
    ẽ
    -0.08
    ä½İ头
    -0.08
     resid
    -0.08
    POSITIVE LOGITS
    æĬķ票
    0.17
    è¯Ħè®®
    0.16
    群ä¼Ĺ
    0.15
    æ°ijæĦı
    0.14
     community
    0.13
    _votes
    0.13
    ä¼ĹçŃ¹
    0.13
    æ°ij主
    0.13
    表åĨ³
    0.13
    ä¼Ĺ
    0.12
    Activations Density 0.182%

    No Known Activations