© 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. 58667
    Prev
    Next
    INDEX
    Explanations

    compilation album book tape

    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
    ä¼ı
    -0.08
    ühl
    -0.08
    æĺ¯æ¯Ķè¾ĥ
    -0.08
    Solo
    -0.08
     Lone
    -0.08
    à²ļ
    -0.08
    ç½ij讯
    -0.08
     Äijá»Ļi
    -0.08
    两ä¸ī
    -0.08
    жа
    -0.08
    POSITIVE LOGITS
    æ±ĩéĽĨ
    0.11
    涵çĽĸäºĨ
    0.11
    èIJĥ
    0.11
    åĮħåIJ«äºĨ
    0.10
    è¾ij
    0.10
    æ±ĩèģļ
    0.10
    涵çĽĸ
    0.10
    èįŁ
    0.09
    æ±ĩæĢ»
    0.09
    第ä¸Ģæī¹
    0.09
    Activations Density 0.153%

    No Known Activations