© 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. 62581
    Prev
    Next
    INDEX
    Explanations

    transferring funds, electrons, power, or data

    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
    èµĿ
    -0.11
    éļıæīĭ
    -0.09
     пÑĥÑĤ
    -0.09
    ä¿®åħ»
    -0.09
    èĿİ
    -0.09
     пÑĥÑĤеÑĪеÑģÑĤв
    -0.09
     redemption
    -0.08
    éĢĢåĽŀ
    -0.08
    åĬŀ
    -0.08
     Berm
    -0.08
    POSITIVE LOGITS
     Transfer
    0.17
     transfer
    0.17
    转移
    0.17
    .transfer
    0.17
    transfer
    0.16
    Transfer
    0.16
     transferring
    0.15
    转移åĪ°
    0.15
    -transfer
    0.15
     transfers
    0.14
    Activations Density 0.131%

    No Known Activations