© 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. 56439
    Prev
    Next
    INDEX
    Explanations

    balance and equilibrium

    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
    ohl
    -0.09
    ä¸įåĸľæ¬¢
    -0.08
    ä¸Ĭå®ĺ
    -0.08
     gerne
    -0.08
    çŀª
    -0.08
    çIJ¼
    -0.08
    éŀŃ
    -0.08
    åı¯ä»¥ä»İ
    -0.08
    igation
    -0.07
    Sortable
    -0.07
    POSITIVE LOGITS
    平衡
    0.41
     balance
    0.37
    balance
    0.33
     Balance
    0.30
    ãĥIJãĥ©ãĥ³ãĤ¹
    0.30
    (balance
    0.29
    Balance
    0.29
    .balance
    0.29
    _balance
    0.27
     balances
    0.26
    Activations Density 0.084%

    No Known Activations