© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 6705
    Prev
    Next
    INDEX
    Explanations

    years

    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
    æĽ´å¤ļ
    -0.10
    è¯Ŀ说
    -0.09
    æŃ£å¥½
    -0.09
    (sa
    -0.09
    _rw
    -0.09
    å¾Ī好
    -0.09
    ramer
    -0.09
    å¾Ī大
    -0.09
    ãģĵãģĿ
    -0.08
    å¹½é»ĺ
    -0.08
    POSITIVE LOGITS
    æĭĶ
    0.09
    ening
    0.09
    æĹłæķĮ
    0.08
    çĺ¾
    0.08
     (>
    0.08
    åĩłæ¬¡
    0.08
    gage
    0.08
    .FLAG
    0.08
    以èĩ³äºİ
    0.08
     tac
    0.08
    Activations Density 0.147%

    No Known Activations