© 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. 50964
    Prev
    Next
    INDEX
    Explanations

    immersed in experiences

    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
    ä¸ĬéŨ
    -0.09
    nox
    -0.09
    à¸ŀลาà¸Ķ
    -0.08
    rieve
    -0.08
    izzard
    -0.08
    entr
    -0.08
     лиÑĪÑĮ
    -0.08
    erna
    -0.08
    avig
    -0.08
    转载
    -0.08
    POSITIVE LOGITS
    ä¹ĭéģĵ
    0.10
    ç½ijå°ıç¼ĸ
    0.10
    åĨįéĢł
    0.10
    å°ĸåı«
    0.09
    auc
    0.09
    å·²ä¹ħçļĦ
    0.09
    æĬij
    0.09
    gence
    0.09
    äºĨä»ĸçļĦ
    0.09
    ä¹ĭæĹħ
    0.09
    Activations Density 0.008%

    No Known Activations