© 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. 21863
    Prev
    Next
    INDEX
    Explanations

    techcrunch.com websites

    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
    éĽĨæĪIJ
    -0.10
    忧
    -0.10
    elijk
    -0.09
    ä¸İæŶ
    -0.09
     Manufact
    -0.09
    acks
    -0.09
    .AddParameter
    -0.09
    andle
    -0.08
     гол
    -0.08
    樯
    -0.08
    POSITIVE LOGITS
    pto
    0.09
    åľ¨æĪijåĽ½
    0.09
    ä¸ĸçķĮ第ä¸Ģ
    0.09
    秫
    0.09
     sco
    0.09
    åľ°éģĵ
    0.08
    æľ«
    0.08
    å°¸
    0.08
    åIJİ代
    0.08
    没æľīå¿ħè¦ģ
    0.08
    Activations Density 0.017%

    No Known Activations