© 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. 35014
    Prev
    Next
    INDEX
    Explanations

    conditional predictions

    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
    æīŃ
    -0.09
    åĨĻéģĵ
    -0.09
    人工
    -0.09
     doubt
    -0.08
    ancy
    -0.08
    ä¸Ńåįİ
    -0.08
    绾
    -0.08
    åħ¼
    -0.08
    marked
    -0.08
    nes
    -0.08
    POSITIVE LOGITS
    åĽ½æ°ij
    0.10
    erk
    0.09
     Freed
    0.09
    parable
    0.09
    è¦ģä¹Ī
    0.09
     ÐĴедÑĮ
    0.09
    æ²Ĩ
    0.09
    èĩ³å°ij
    0.08
    angen
    0.08
    好äºĭ
    0.08
    Activations Density 0.058%

    No Known Activations