© 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. 5211
    Prev
    Next
    INDEX
    Explanations

    end of sentence marker

    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
    ORIZ
    -0.09
    gage
    -0.09
    عÙĦاÙħ
    -0.08
    spar
    -0.08
     Sak
    -0.08
    lassen
    -0.08
    forcer
    -0.08
    åħ¬çĦ¶
    -0.08
    áticas
    -0.08
     Dest
    -0.08
    POSITIVE LOGITS
    ç½ij绾ç§ijæĬĢ
    0.09
    大家ä¸Ģèµ·
    0.08
    æĶ¶è´¹ç«Ļ
    0.08
    å¾Īå¤ļæľĭåıĭ
    0.08
    çļĦæĹ¥åŃIJ
    0.08
    笥
    0.08
    åĭ¤å¥ĭ
    0.08
    ä¹ĭç±»çļĦ
    0.08
    ä¸įå¤ļ
    0.08
    ï¸ı
    0.08
    Activations Density 0.094%

    No Known Activations