© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 51498
    Prev
    Next
    INDEX
    Explanations

    developed, advanced, mature

    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
    Tac
    -0.08
     bè
    -0.08
    å§ĭç»ĪåĿļæĮģ
    -0.08
    ç«ĭéĿ¢
    -0.08
     DAR
    -0.08
    åħľ
    -0.08
    à¹ģฮ
    -0.08
     Tac
    -0.08
    éĩįä¸Ńä¹ĭéĩį
    -0.08
    è§Ī
    -0.08
    POSITIVE LOGITS
    æĪIJçĨŁ
    0.24
    æĪIJçĨŁçļĦ
    0.23
    åıijè¾¾
    0.22
    å®ĮåĸĦ
    0.20
    å®ĮåĸĦçļĦ
    0.19
     mature
    0.16
    å®Įå¤ĩ
    0.15
    åĴĮå®ĮåĸĦ
    0.15
     maturity
    0.15
     sophisticated
    0.14
    Activations Density 0.108%

    No Known Activations