© 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. 34512
    Prev
    Next
    INDEX
    Explanations

    properties and activities

    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
    豪
    -0.10
    æľįåĬ¡æľºæŀĦ
    -0.10
     Libre
    -0.10
     Nimbus
    -0.09
     гÑĢаÑĦик
    -0.09
    Ñĭваем
    -0.09
    æĹłåĬ©
    -0.09
    为ä¹ĭ
    -0.09
    alles
    -0.09
    å¹²äºĭ
    -0.09
    POSITIVE LOGITS
    ä½ľçĶ¨
    0.16
    åĬŁæķĪ
    0.12
     qualities
    0.11
    æķĪåĬĽ
    0.10
     properties
    0.10
    天çĦ¶
    0.10
     capabilities
    0.09
    å¾Ī强
    0.09
     Runner
    0.09
    éĩįè¦ģä½ľçĶ¨
    0.09
    Activations Density 0.196%

    No Known Activations