© 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. 4499
    Prev
    Next
    INDEX
    Explanations

    collecting data or information

    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
     phó
    -0.10
    æİ¥æīĭ
    -0.09
    ä¸Ģåľº
    -0.09
    åıĸãĤĬ
    -0.09
    æµģæĺŁ
    -0.09
    hole
    -0.09
    ãģıãĤĮ
    -0.08
    itta
    -0.08
    chron
    -0.08
    ValueCollection
    -0.08
    POSITIVE LOGITS
    (Collectors
    0.10
    稷
    0.10
    ×ķת
    0.10
    èµ·ä¾Ĩ
    0.09
     инÑĦоÑĢмаÑĨиÑİ
    0.09
    ivity
    0.09
    ters
    0.09
    andre
    0.09
    è¶³å¤ŁçļĦ
    0.09
    AndServe
    0.09
    Activations Density 0.029%

    No Known Activations