© 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. 58186
    Prev
    Next
    INDEX
    Explanations

    Ganga, Ganesha, Gag

    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
    移
    -0.10
     Newman
    -0.10
    åĩłåĪĨ
    -0.10
    å¿ĺ
    -0.09
    鹤
    -0.08
    å·¥ä½ľç«Ļ
    -0.08
    æ°¸ä¸į
    -0.08
    å¼Ľ
    -0.08
    æĿ¥åģļ
    -0.08
    çĶļèĩ³æĺ¯
    -0.08
    POSITIVE LOGITS
    举
    0.09
    æĭ§
    0.08
    æµĬ
    0.08
     sve
    0.08
    两类
    0.08
     dereg
    0.08
    esar
    0.08
    éĵķ
    0.08
    èĦ²
    0.08
    Ñģком
    0.08
    Activations Density 0.083%

    No Known Activations