© 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. 28057
    Prev
    Next
    INDEX
    Explanations

    submission, escape, abstract, 0, 6, strict

    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
    æĤłæĤł
    -0.10
    çŁ¥æĥħ
    -0.10
    lish
    -0.09
    被æīĵ
    -0.09
    ä»Ģä¹Īä¸ľè¥¿
    -0.09
    æĪĺæĸĹ
    -0.09
    æ²½
    -0.09
    å¾Ĵ
    -0.09
    æ®´
    -0.09
    æĭ³
    -0.09
    POSITIVE LOGITS
    å¤§éĽ¨
    0.09
    abra
    0.09
    arel
    0.09
    è½¬åŁºåĽł
    0.08
    寻æ±Ĥ
    0.08
    导åIJij
    0.08
    ç¬ijè¯Ŀ
    0.08
    ä¸įæĸŃ
    0.08
    uos
    0.08
    é¢ijé¢ij
    0.08
    Activations Density 0.008%

    No Known Activations