© 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. 26563
    Prev
    Next
    INDEX
    Explanations

    served or administered

    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
    鸥
    -0.12
    çĪ¹
    -0.10
    è¦ģ说
    -0.09
    oppel
    -0.09
    妥åĸĦ
    -0.09
     Landing
    -0.09
    èĢIJçĶ¨
    -0.09
    æĩĤäºĭ
    -0.09
    çĪ»
    -0.09
    ick
    -0.09
    POSITIVE LOGITS
    åĿİ
    0.10
    ulum
    0.09
    è¿Ļå°±æĺ¯
    0.09
    izu
    0.09
    apia
    0.09
    orsi
    0.09
    izzazione
    0.08
    ä»Ģä¹Īæł·
    0.08
     alongside
    0.08
    à¹ģà¸ļà¸ļ
    0.08
    Activations Density 0.016%

    No Known Activations