© 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. 1663
    Prev
    Next
    INDEX
    Explanations

    simulation and Monte Carlo

    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
    稿
    -0.08
    è´¸æĺĵ
    -0.08
    æ§
    -0.08
     Kou
    -0.08
    第ä¸īæĸ¹
    -0.08
    oid
    -0.08
     traded
    -0.08
     stall
    -0.08
    REET
    -0.08
    åĶ
    -0.08
    POSITIVE LOGITS
    ä»¿çľŁ
    0.15
     simulation
    0.13
     Simulation
    0.13
    模æĭŁ
    0.13
    Simulation
    0.13
    simulation
    0.12
    imulation
    0.10
    èĿĹ
    0.10
     simulations
    0.09
    ModelProperty
    0.09
    Activations Density 0.272%

    No Known Activations