© 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. 30343
    Prev
    Next
    INDEX
    Explanations

    still or afterwards

    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
    çľĭä»ĸ
    -0.09
    æĸĹ
    -0.08
    åĴĮä»ĸçļĦ
    -0.08
    梦æĥ³
    -0.08
    alis
    -0.08
    ute
    -0.08
     Daniels
    -0.08
     Kut
    -0.08
    å½»
    -0.08
    eka
    -0.08
    POSITIVE LOGITS
    è¿ĺä¸į
    0.10
    è¿ĺä¸įæĺ¯
    0.09
    _extractor
    0.09
    ä¸įæĸŃåĪĽæĸ°
    0.09
    illet
    0.09
    æīįå¹²
    0.09
    大è¡Ĺ
    0.08
    åİ¿åŁİ
    0.08
    åĢ¾æĸľ
    0.08
    åıijæĮ¥äºĨ
    0.08
    Activations Density 0.036%

    No Known Activations