© 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. 36400
    Prev
    Next
    INDEX
    Explanations

    long duration or extent

    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
    лаг
    -0.11
    大佬
    -0.10
    çĽİ
    -0.09
    ết
    -0.09
    å¾Īå°ı
    -0.09
    èĻı
    -0.09
    ãĥ¥
    -0.09
    纶
    -0.09
    LOG
    -0.09
    tractive
    -0.08
    POSITIVE LOGITS
    evity
    0.19
    ueur
    0.19
    itud
    0.18
    itudes
    0.16
    -lived
    0.16
    -lasting
    0.16
    -awaited
    0.14
     ago
    0.13
    ITUDE
    0.13
    ened
    0.13
    Activations Density 0.101%

    No Known Activations