© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 38175
    Prev
    Next
    INDEX
    Explanations

    organic followed by noun

    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
    è¯ļæĦı
    -0.10
    رة
    -0.09
    女ç¥ŀ
    -0.08
    RootElement
    -0.08
    æĦıåĽ¾
    -0.08
    lö
    -0.08
    èį¡
    -0.08
     jugg
    -0.08
    çľ¼æ³ª
    -0.08
    æ·ij
    -0.08
    POSITIVE LOGITS
    /UI
    0.09
    /org
    0.09
    丰å¯Įå¤ļ彩
    0.09
    çĩĶ
    0.09
    éĥ¨ä»½
    0.09
    åĦĴ
    0.09
    æ®ĭçķĻ
    0.08
    èĩªåĬ¨
    0.08
    æĢ¥åī§
    0.08
     данного
    0.08
    Activations Density 0.092%

    No Known Activations