© 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. 34302
    Prev
    Next
    INDEX
    Explanations

    relative clauses connecting things

    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
    å®ĥæĺ¯
    -0.10
    éĥ½ä¸įæĺ¯
    -0.10
    è¿ĻéĩĮæĺ¯
    -0.10
     ê·¸ê²ĥ
    -0.10
    å·²æĪIJ为
    -0.10
    ä¸Ģæł·çļĦ
    -0.10
    è¿Ļä¹Łæĺ¯
    -0.10
    æĺ¯æĪij
    -0.10
    æį¢æĪIJ
    -0.09
    vince
    -0.09
    POSITIVE LOGITS
    æĹ¢åı¯ä»¥
    0.10
     pl
    0.09
    å®ļäºĨ
    0.08
    çī¯
    0.08
    ä¸įä»ħè¦ģ
    0.08
    ä¸įä»ħ
    0.08
    æĹ¢è¦ģ
    0.08
     HD
    0.08
    æŀģæĺĵ
    0.08
    at
    0.08
    Activations Density 0.074%

    No Known Activations