© 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. 52707
    Prev
    Next
    INDEX
    Explanations

    offering help or assistance

    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
    人æīį
    -0.10
    æļ´
    -0.10
    acin
    -0.09
    oot
    -0.08
    è¾ĵäºĨ
    -0.08
     eros
    -0.08
    acular
    -0.08
    ypes
    -0.08
     Chambers
    -0.08
    ä¸ĵä¸ļæĬĢæľ¯
    -0.08
    POSITIVE LOGITS
    åħ¨ç¨ĭ
    0.12
    æ¯ıä¸Ģ个
    0.10
    让æĤ¨
    0.10
    INC
    0.09
    å±ķé¦Ĩ
    0.09
    æĤ¨çļĦ
    0.09
    åħ¨è¿ĩç¨ĭ
    0.08
    åijĬè¯īä½ł
    0.08
    agg
    0.08
    éĢīè´Ń
    0.08
    Activations Density 0.049%

    No Known Activations