© 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. 30101
    Prev
    Next
    INDEX
    Explanations

    for the

    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
    çİ°æľī
    -0.09
    æĭŃ
    -0.09
    èģ¿
    -0.09
    å´§
    -0.09
    称ä¹ĭ
    -0.09
    æ¯ıä¸Ģ
    -0.09
    ÑĪен
    -0.09
    ymi
    -0.09
    æıIJåĩºçļĦ
    -0.09
    arget
    -0.08
    POSITIVE LOGITS
    çļĦåıijçĶŁ
    0.14
    çļĦåıijå±ķ
    0.13
    çļĦåĪ°æĿ¥
    0.13
    à¸ģาร
    0.12
     viá»ĩc
    0.11
    çļĦåŃĺåľ¨
    0.11
    çĶŁåij½çļĦ
    0.10
    çļĦè¿ĽæŃ¥
    0.10
    çļĦåıĺåĮĸ
    0.10
    产åĵģçļĦ
    0.09
    Activations Density 0.603%

    No Known Activations