© 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. 21778
    Prev
    Next
    INDEX
    Explanations

    VHF frequencies or cabin

    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
    æĶĺ
    -0.10
    é©´
    -0.09
    å¢ĥçķĮ
    -0.09
    åľ¨è·¯ä¸Ĭ
    -0.08
    èµĭ
    -0.08
    aurus
    -0.08
    ç¢ī
    -0.08
    æļ´
    -0.08
    åĩ¡æĺ¯
    -0.08
     misc
    -0.08
    POSITIVE LOGITS
    åħ»èĢģ
    0.10
    زÙħ
    0.09
    åŃ¦æł¡çļĦ
    0.09
    sonian
    0.09
    ä¸Ģç³»åĪĹ
    0.09
     Picks
    0.09
    ilst
    0.09
    leo
    0.08
    çĶµè§Ĩæľº
    0.08
    ä»ĸè¿ĺ
    0.08
    Activations Density 0.007%

    No Known Activations