© 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. 50947
    Prev
    Next
    INDEX
    Explanations

    or no / if any

    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
    ä¸īåĪĨä¹ĭä¸Ģ
    -0.10
    æĬĢæľ¯åĴĮ
    -0.10
    ä¸įå°½
    -0.10
    æĹ¢æĺ¯
    -0.10
    apl
    -0.10
    æľīä»»ä½ķ
    -0.10
    è´¨éĩıåĴĮ
    -0.10
     ÑħоÑĤÑĮ
    -0.09
    åĴĮ社ä¼ļ
    -0.09
    æºĺ
    -0.09
    POSITIVE LOGITS
     RHS
    0.09
    ard
    0.09
    å·
    0.08
     Ñģамого
    0.08
     stor
    0.08
    á»Ļc
    0.08
    ITH
    0.08
    ish
    0.08
    åĩ¹
    0.08
    z
    0.08
    Activations Density 0.044%

    No Known Activations