© 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. 30540
    Prev
    Next
    INDEX
    Explanations

    lost or got

    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
    .appspot
    -0.08
    ç½ij绾ç§ijæĬĢ
    -0.08
     Rein
    -0.08
    åĽĽå·Ŀçľģ
    -0.08
     ex
    -0.08
    è¾İ
    -0.08
    å¹²ä»Ģä¹Ī
    -0.08
    nable
    -0.08
     awake
    -0.08
    让å®ĥ
    -0.08
    POSITIVE LOGITS
    æŁIJæŁIJ
    0.10
     XYZ
    0.09
    âķ³
    0.09
    PRS
    0.09
    ãģ°ãģĭãĤĬ
    0.09
    æŁIJ
    0.09
    æŁIJ个
    0.09
    è´µ
    0.09
    æĭĵ宽
    0.09
    åıªè§ģ
    0.09
    Activations Density 0.150%

    No Known Activations