© 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. 55389
    Prev
    Next
    INDEX
    Explanations

    opposition and dissent

    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
    鬼
    -0.11
    สà¹Ģà¸ķ
    -0.10
    _hooks
    -0.10
    æĻ®
    -0.10
     Lund
    -0.09
    (dy
    -0.08
    åѦåijĺ
    -0.08
    综
    -0.08
    à¸ģรรม
    -0.08
     зан
    -0.08
    POSITIVE LOGITS
    å¼Ĥè®®
    0.15
     dissent
    0.14
    æī¹è¯Ħ
    0.11
    åıį对
    0.11
     opposition
    0.11
    忤
    0.11
    æĮijæĪĺ
    0.10
    转弯
    0.10
    诤
    0.10
    æķ¢
    0.09
    Activations Density 0.090%

    No Known Activations