© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 37450
    Prev
    Next
    INDEX
    Explanations

    remind you or us

    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
    éĥ¤
    -0.08
     liken
    -0.08
    ä»Ģä¹Īäºĭ
    -0.08
    acher
    -0.07
    an
    -0.07
    ilyn
    -0.07
    说å¾Ĺ
    -0.07
    cou
    -0.07
    æĽ´å¤ļä¿¡æģ¯
    -0.07
     bothering
    -0.07
    POSITIVE LOGITS
     us
    0.15
    人åĢij
    0.13
    大家
    0.13
    人们
    0.13
    ä¸ĸ人
    0.13
     Ñģобой
    0.12
    大家åĪĨ享
    0.12
    åĪ«äºº
    0.11
    为æŃ¢
    0.11
    orc
    0.11
    Activations Density 0.040%

    No Known Activations