© 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. 62605
    Prev
    Next
    INDEX
    Explanations

    by profession or trade

    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
    顾éĹ®
    -0.10
     ì»
    -0.10
    лиÑĤ
    -0.10
    檩
    -0.09
    .GetText
    -0.09
    Enumerator
    -0.09
    icum
    -0.09
    æĤĶ
    -0.09
    orman
    -0.09
    å¾®åķĨ
    -0.09
    POSITIVE LOGITS
    è¿ĻæĿ¡è·¯
    0.10
    éħ¯
    0.09
    tre
    0.09
    è¿Ļçīĩ
    0.09
    åĬ¿
    0.09
    è¿Ļç§įæĸ¹å¼ı
    0.08
    Âł
    0.08
    åĬŀäºĭ
    0.08
     misplaced
    0.08
     sake
    0.08
    Activations Density 0.097%

    No Known Activations