© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 40068
    Prev
    Next
    INDEX
    Explanations

    drug development

    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
    ç§¦åĽ½
    -0.10
    las
    -0.09
    人å±ħ
    -0.09
    æķŀå¼Ģ
    -0.09
    åı¥
    -0.09
    ä¸įæ¸ħ
    -0.08
    黾
    -0.08
    stringValue
    -0.08
    伪
    -0.08
    秦
    -0.08
    POSITIVE LOGITS
    çłĶåıij
    0.11
    å¼Ģåıij
    0.11
    çłĶåĪ¶
    0.10
    çļĦçłĶåıij
    0.10
    çłĶåıijä¸Ńå¿ĥ
    0.10
    development
    0.09
     development
    0.09
    _CODEC
    0.09
    èį¯çī©
    0.09
    æݨæµĭ
    0.09
    Activations Density 0.110%

    No Known Activations