© 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. 4844
    Prev
    Next
    INDEX
    Explanations

    but followed by contrast/elaboration

    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
    ëį°
    -0.09
    Mismatch
    -0.09
    çļĦå°±æĺ¯
    -0.09
    æĺİæĺİ
    -0.09
    åŁł
    -0.08
    own
    -0.08
    çĿĢä»ĸ
    -0.08
    åĩĨ
    -0.08
    çļĦæĺ¯
    -0.08
    å«Į
    -0.08
    POSITIVE LOGITS
    åı¯ä»¥åľ¨
    0.10
    赶赴
    0.10
    åı¯ä»¥æł¹æį®
    0.09
    åħ¶ä»ĸåĽ½å®¶
    0.09
    èĮĦ
    0.09
    ouden
    0.09
    æŃ¤é¡¹
    0.09
    ä»ħä¾ĽåıĤèĢĥ
    0.09
    èݲ
    0.08
    åı¯ä»¥éĢīæĭ©
    0.08
    Activations Density 0.122%

    No Known Activations