© 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. 34548
    Prev
    Next
    INDEX
    Explanations

    meaning, etymology, origin

    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
     Suspension
    -0.10
    Narrated
    -0.09
    çľ©
    -0.09
    eer
    -0.09
    空åīį
    -0.09
    Susp
    -0.08
    ök
    -0.08
    ior
    -0.08
    éĺĶ
    -0.08
    ettel
    -0.08
    POSITIVE LOGITS
    å¯ĵæĦı
    0.18
    象å¾ģ
    0.17
    åIJ«ä¹ī
    0.16
    æĦıä¹ī
    0.16
    解éĩĬ
    0.15
     meanings
    0.14
    æĦıåij³
    0.13
     meaning
    0.13
    åĨħ涵
    0.12
    çļĦæĦıä¹ī
    0.12
    Activations Density 0.118%

    No Known Activations