© 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. 53047
    Prev
    Next
    INDEX
    Explanations

    allow time

    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
    åŀ£
    -0.09
    yal
    -0.09
    _soc
    -0.09
    dio
    -0.08
    ç¦ıå¾·
    -0.08
    å¸ĸ
    -0.08
    岸
    -0.08
    å¹Ħ
    -0.08
    èIJ½ä¸ĭ
    -0.08
    è´ŀ
    -0.08
    POSITIVE LOGITS
    æĮ¹
    0.09
    æŀ§
    0.09
    ssa
    0.09
    鸳
    0.08
    ERIC
    0.08
    å¾ľ
    0.08
    ãĥ³ãĤ°
    0.08
    æĹĮ
    0.08
    assy
    0.08
    .between
    0.08
    Activations Density 0.003%

    No Known Activations