© 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. 57644
    Prev
    Next
    INDEX
    Explanations

    during or due to

    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
    uevo
    -0.10
    天çĶŁ
    -0.09
    æĭĽ
    -0.09
    以便
    -0.09
    æļĹ
    -0.08
     дополниÑĤелÑĮно
    -0.08
    ä½Ĩä»ĸ们
    -0.08
    reck
    -0.08
    ç¿ģ
    -0.08
    suming
    -0.08
    POSITIVE LOGITS
     ÙĪعدÙħ
    0.10
    _fixture
    0.09
     followed
    0.09
    çĪ¹
    0.09
    Fixture
    0.09
    à¹ģละà¸ģาร
    0.09
    Advertisements
    0.09
     bestimm
    0.08
     oneself
    0.08
    -shared
    0.08
    Activations Density 0.263%

    No Known Activations