© 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. 63154
    Prev
    Next
    INDEX
    Explanations

    program input/output

    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
    æľīåĪ©äºİ
    -0.10
    åł±
    -0.09
    éħĿéħ¿
    -0.09
    ä¸Ģä¸ĭåŃIJå°±
    -0.09
    ARAM
    -0.09
     Ferd
    -0.09
    åĨįåİ»
    -0.09
    ãģĤãģ®
    -0.09
    è¿Ļåı¥è¯Ŀ
    -0.09
    è¿Ļç§įæĸ¹å¼ı
    -0.09
    POSITIVE LOGITS
    ç®ĢåįķçļĦ
    0.12
    çļĦç§ĺå¯Ĩ
    0.09
     simple
    0.09
     Mein
    0.09
    ä½Ĩä¸įéĻIJ
    0.08
    Æ°
    0.08
    ç®Ģåįķ
    0.08
    ï¸
    0.08
    çį
    0.08
    simple
    0.08
    Activations Density 1.449%

    No Known Activations