© 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. 47823
    Prev
    Next
    INDEX
    Explanations

    conditional 'yes' answers

    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®ł
    -0.11
    åį´åıĪ
    -0.10
    ALLE
    -0.09
    arkan
    -0.09
    ç®Ĺæĺ¯
    -0.09
    nel
    -0.08
    enga
    -0.08
    åĬ¡
    -0.08
     ÑįкономиÑĩеÑģк
    -0.08
    .freeze
    -0.08
    POSITIVE LOGITS
    è¿ĻäºĽéĹ®é¢ĺ
    0.12
    以ä¸Ĭ
    0.10
    çļĦçŃĶæ¡Ī
    0.10
    æĺ¨æĹ¥
    0.09
    èĩ³æѤ
    0.09
    æİĮæı¡äºĨ
    0.09
     yes
    0.09
    è¿Ļæł·çļĦè¯Ŀ
    0.08
    æĺ¨
    0.08
    oud
    0.08
    Activations Density 0.014%

    No Known Activations