© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 53251
    Prev
    Next
    INDEX
    Explanations

    curtain and curtains

    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
    iton
    -0.11
    鼶ç¢İ
    -0.10
    é»į
    -0.10
     Shapiro
    -0.09
    Ãłn
    -0.09
    å¿ĥæĦ¿
    -0.09
    åĿļ硬
    -0.09
    书记
    -0.09
    åIJĮæľŁ
    -0.09
    elled
    -0.09
    POSITIVE LOGITS
    帷
    0.11
    ières
    0.10
    çŀŃ
    0.09
     sos
    0.09
    èĭŁ
    0.09
    æ¨Ĭ
    0.09
    窦
    0.09
    ees
    0.09
    etten
    0.09
    alam
    0.09
    Activations Density 0.011%

    No Known Activations