© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 22181
    Prev
    Next
    INDEX
    Explanations

    past, present, future

    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
    adar
    -0.09
    è±ī
    -0.09
    otch
    -0.09
    oner
    -0.09
    hurst
    -0.09
    -calendar
    -0.09
    åŃ°
    -0.08
    ugo
    -0.08
    ä»İå°ı
    -0.08
    鹦
    -0.08
    POSITIVE LOGITS
    以èĩ³äºİ
    0.12
    ä»Ĭ
    0.11
    å½ĵä¸ĭ
    0.11
    ä»ĬåIJİ
    0.10
    ä»įåľ¨
    0.10
    .future
    0.10
    ä»įçĦ¶
    0.10
    current
    0.10
    çİ°åľ¨çļĦ
    0.10
    ãģĵãĤĮãģĭãĤī
    0.10
    Activations Density 0.025%

    No Known Activations