© 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. 33849
    Prev
    Next
    INDEX
    Explanations

    running or extending in a direction

    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
    æľŁåĨħ
    -0.10
    èĦ¸
    -0.10
    æ»ŀ
    -0.09
    ä¸įä¸Ĭ
    -0.09
     fly
    -0.09
    anton
    -0.09
    Intern
    -0.09
    ç¹ĩ
    -0.09
    èĮħ
    -0.09
    å¿Ļç¢Į
    -0.08
    POSITIVE LOGITS
    延伸
    0.20
     extend
    0.13
    缴åĪ°
    0.12
    ä¸Ģ缴åĪ°
    0.12
    延ç»Ń
    0.12
    èĶĵ延
    0.11
     extends
    0.11
     extending
    0.11
    缴èĩ³
    0.11
    å¾ĢåIJİ
    0.10
    Activations Density 0.110%

    No Known Activations