© 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. 10814
    Prev
    Next
    INDEX
    Explanations

    Prime Minister

    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
    re
    -0.10
    çł¥
    -0.09
    ä¹±
    -0.09
    spath
    -0.09
    ../../../
    -0.08
    inx
    -0.08
    osis
    -0.08
    swer
    -0.08
    饿
    -0.08
    abbage
    -0.07
    POSITIVE LOGITS
    åħ¼
    0.10
    ä¸ĭ令
    0.10
    磼
    0.10
    .tie
    0.10
    ê³¼ìłķ
    0.10
    RODUCTION
    0.10
    ç®į
    0.10
     Revel
    0.10
    vely
    0.09
    廨
    0.09
    Activations Density 0.010%

    No Known Activations