© 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. 54274
    Prev
    Next
    INDEX
    Explanations

    French and English words, names

    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
    eties
    -0.09
    èįł
    -0.09
    lops
    -0.08
    æ°¤
    -0.08
    goog
    -0.08
     goog
    -0.08
    éĥ¨åĪĨåĨħ容
    -0.08
    éĿĴå±±
    -0.08
    ä¸ĢåĪĻ
    -0.08
    çĶŁäº§çº¿
    -0.08
    POSITIVE LOGITS
    essel
    0.09
     плоÑħо
    0.08
    页
    0.08
    å¥Ķ
    0.08
    俨
    0.08
     reconcile
    0.08
    åıĮéĩį
    0.08
     Bourbon
    0.08
    æ¼³
    0.08
    Ñİ
    0.08
    Activations Density 0.062%

    No Known Activations