© 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. 35484
    Prev
    Next
    INDEX
    Explanations

    biological processes and changes

    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
    ç³ł
    -0.09
    åºij
    -0.09
    åľ°çĭ±
    -0.08
    çļĦåºĶçĶ¨
    -0.08
    纽带
    -0.08
    èĥ¸åı£
    -0.08
    lient
    -0.08
    .community
    -0.08
    æĹłç¼Ŀ
    -0.08
    人éĢł
    -0.08
    POSITIVE LOGITS
    anton
    0.10
    åĪĨå·¥
    0.08
    ultimate
    0.08
    ÑĢаб
    0.08
    åİļåİļçļĦ
    0.08
    åĢĴæĺ¯
    0.08
    idy
    0.08
    éĩįä»»
    0.08
     Mahm
    0.08
     reinc
    0.08
    Activations Density 0.784%

    No Known Activations