© 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. 22550
    Prev
    Next
    INDEX
    Explanations

    explaining or translating

    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
    çĩ¥
    -0.11
    ä¸Ģä¸Ģ
    -0.10
    UNE
    -0.09
    对çħ§
    -0.08
    ä¸Ģéĥ¨
    -0.08
    Ïİ
    -0.08
    ROWN
    -0.07
    建
    -0.07
    .ep
    -0.07
    åĬŀ
    -0.07
    POSITIVE LOGITS
    æĶ¹æĪIJ
    0.12
    表述
    0.12
    两åı¥
    0.11
    phrase
    0.11
    æį¢æĪIJ
    0.11
    è¿Ļä¹Ī说
    0.11
    è¿Ļåı¥è¯Ŀ
    0.11
    è¿Ļæł·è¯´
    0.11
    çļĦ说æ³ķ
    0.10
    æĶ¹ä¸º
    0.10
    Activations Density 0.116%

    No Known Activations