© 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. 39768
    Prev
    Next
    INDEX
    Explanations

    positive and negative evaluations

    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
    -Jun
    -0.09
    åīª
    -0.09
     lã
    -0.08
    å©ķ
    -0.08
    æĥħæĻ¯
    -0.08
    å®Įç¾İ
    -0.08
    åĬ£åĬ¿
    -0.08
     Banc
    -0.08
     Ñģка
    -0.08
    ä¼´
    -0.08
    POSITIVE LOGITS
     testament
    0.11
    屯
    0.11
    èĩªèº«çļĦ
    0.11
    æľ¬èº«çļĦ
    0.10
    èį£å¹¸
    0.10
    èµĽ
    0.10
    泺
    0.09
    æīĢåľ¨
    0.09
    Ahead
    0.09
    æ²¥
    0.09
    Activations Density 0.039%

    No Known Activations