© 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. 38919
    Prev
    Next
    INDEX
    Explanations

    specialist and specialization

    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
     наÑģел
    -0.09
    cheme
    -0.08
    ä¿Ŀ
    -0.08
    被éªĹ
    -0.08
    _sched
    -0.08
    æĹłå£°
    -0.08
    å¸Ŀ
    -0.08
    åĭī
    -0.08
    æĶ¯éħį
    -0.08
    Disposed
    -0.08
    POSITIVE LOGITS
    åĪĨå·¥
    0.21
     specialization
    0.21
    ä¸ĵ
    0.19
    ä¸ĵèģĮ
    0.18
    ä¸ĵä¸ļåĮĸ
    0.17
     niche
    0.16
    å°Ī
    0.16
     specialize
    0.16
     specialty
    0.15
     specializing
    0.15
    Activations Density 0.110%

    No Known Activations