© 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. 57681
    Prev
    Next
    INDEX
    Explanations

    law and order, disorder, chaos

    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
    åIJĪ
    -0.11
    urette
    -0.09
    arily
    -0.09
    è¥Ħ
    -0.09
    æĿ¥ä¸įåıĬ
    -0.09
    强çĥĪ
    -0.09
    --------------------------------------------------------------------------↵
    -0.09
    orial
    -0.09
    ä¸įåIJĪ
    -0.09
    ç¢Ĺ
    -0.09
    POSITIVE LOGITS
    秩åºı
    0.12
     minded
    0.11
    å±ĢéĿ¢
    0.10
    æ··ä¹±
    0.10
    -minded
    0.10
    liness
    0.09
     chaos
    0.09
    son
    0.09
     addTarget
    0.09
     Minds
    0.08
    Activations Density 0.016%

    No Known Activations