© 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. 51331
    Prev
    Next
    INDEX
    Explanations

    time, specific concepts, and ideas

    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
    jan
    -0.09
    oren
    -0.08
     ниÑĩ
    -0.08
    upt
    -0.08
    eler
    -0.08
    otor
    -0.08
     Burton
    -0.08
     Immediate
    -0.08
    UPI
    -0.08
    dr
    -0.08
    POSITIVE LOGITS
    ness
    0.13
    æĢ§çļĦ
    0.12
    çİ©æĦı
    0.11
    NESS
    0.11
    ity
    0.10
    ä¸įçŁ¥ä¸įè§ī
    0.10
    ly
    0.09
    çļĦæīĢæľī
    0.09
     обÑĢазом
    0.09
    ä¸įå·²
    0.09
    Activations Density 0.722%

    No Known Activations