© 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. 30731
    Prev
    Next
    INDEX
    Explanations

    probability density, distribution, inequality

    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
    åĬŁå¤«
    -0.11
    aring
    -0.10
    ction
    -0.09
    工夫
    -0.09
    ped
    -0.09
    é¥ķ
    -0.09
    azor
    -0.09
    iger
    -0.09
    çĶij
    -0.09
    river
    -0.08
    POSITIVE LOGITS
    iotics
    0.11
    /stat
    0.11
    LocalizedString
    0.10
    ably
    0.10
    idente
    0.09
    nel
    0.09
    æķŀå¼Ģ
    0.09
    ä¸ĢäºĮ
    0.09
    eki
    0.09
    mente
    0.09
    Activations Density 0.052%

    No Known Activations