© 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. 9895
    Prev
    Next
    INDEX
    Explanations

    grumpy character

    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
    arend
    -0.10
    åı¸
    -0.09
     rÃłng
    -0.09
     Lawn
    -0.09
    身价
    -0.09
     há»ĵng
    -0.09
    å©Ĭ
    -0.08
    ÑģÑĮ
    -0.08
    ì±ħ
    -0.08
    缨
    -0.08
    POSITIVE LOGITS
    èĦ¾æ°Ķ
    0.15
    ä¸įåĸľæ¬¢
    0.12
    æĢ§æł¼
    0.11
    æĢģ度
    0.10
    éĥģ
    0.10
     gr
    0.10
    åѤçĭ¬
    0.10
     mood
    0.10
    æĤ²è§Ĥ
    0.10
    é¢Ħå®ļ
    0.10
    Activations Density 0.067%

    No Known Activations