© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 21188
    Prev
    Next
    INDEX
    Explanations

    promotions

    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´¨éĩıåĴĮ
    -0.09
    pts
    -0.08
    并ä¸įå¤ļ
    -0.08
     pity
    -0.08
    å¤ĸç±į
    -0.08
    çĶŁäº§åĴĮ
    -0.08
    èĦ±è´«èĩ´å¯Į
    -0.08
    积æŀģæĢ§
    -0.07
    èĢĮçİ°åľ¨
    -0.07
    èķĥ
    -0.07
    POSITIVE LOGITS
     ÑĥÑģл
    0.09
    ÑĢаÑģÑĤ
    0.09
    .CONTENT
    0.09
    å¤ĩ
    0.09
    çħ³
    0.08
    ãģĭãģij
    0.08
    ä¹ĭæĺŁ
    0.08
    .strict
    0.08
    åīįèĢħ
    0.08
    stance
    0.08
    Activations Density 0.848%

    No Known Activations