© 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. 18378
    Prev
    Next
    INDEX
    Explanations

    are followed by description or question

    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
     инÑĦоÑĢмаÑĨии
    -0.11
    pees
    -0.10
     stuff
    -0.09
    åħ¶ä¸Ńä¹ĭä¸Ģ
    -0.09
     Orchestra
    -0.09
    stuff
    -0.09
    ä¹ĭä¸Ģ
    -0.08
     обоÑĢÑĥдование
    -0.08
    浦
    -0.08
    å¥Ĺ
    -0.08
    POSITIVE LOGITS
    åıĤèĢĥèµĦæĸĻ
    0.09
    quence
    0.09
    ä¸įçĽ¸ä¿¡
    0.09
    çij¾
    0.09
    å½ĵä½ľ
    0.08
    å¤ļ个
    0.08
    说çļĦè¯Ŀ
    0.08
    æľ¬çĿĢ
    0.08
    ently
    0.08
    å¹´æĿ¥
    0.08
    Activations Density 0.213%

    No Known Activations