© 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. 20087
    Prev
    Next
    INDEX
    Explanations

    proper nouns and names

    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
    çľī
    -0.10
    istas
    -0.08
    ä¸įæĩĪ
    -0.08
    æ½į
    -0.08
    éľĩ
    -0.08
    izzes
    -0.08
    åĢŃ
    -0.08
    ì°Į
    -0.08
    å±Ī
    -0.08
    Anonymous
    -0.08
    POSITIVE LOGITS
    èĤ©èĨĢ
    0.10
    æĽ³
    0.09
     Narc
    0.09
    angel
    0.09
    模仿
    0.08
    æĻļä¼ļ
    0.08
    ä»ĬåIJİ
    0.08
    翾
    0.08
    antic
    0.08
    alignment
    0.08
    Activations Density 0.183%

    No Known Activations