© 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. 56256
    Prev
    Next
    INDEX
    Explanations

    privacy policy

    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
    ç´«
    -0.08
    çĵ¢
    -0.08
    å·ħ
    -0.08
    agers
    -0.08
    REC
    -0.08
    åĬĪ
    -0.08
    åĿ¤
    -0.08
    PLAN
    -0.08
    {}_
    -0.08
    raits
    -0.07
    POSITIVE LOGITS
    éĿŀ常好çļĦ
    0.11
    éĿŀ常éĩįè¦ģ
    0.09
    å¾ĹäºĨ
    0.09
    alsy
    0.09
    说ä¸įåĩº
    0.09
    eneg
    0.09
    鬼
    0.09
    åIJ¬è¿ĩ
    0.09
    ä¸įä¼ļåĨį
    0.09
    ä»İä¸ļ
    0.08
    Activations Density 0.055%

    No Known Activations