© 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. 48854
    Prev
    Next
    INDEX
    Explanations

    portal gateway

    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
    VRT
    -0.09
     Moor
    -0.08
    /live
    -0.08
    裤åŃIJ
    -0.08
    梢
    -0.08
    åıĪæľī
    -0.08
    uated
    -0.08
    -navigation
    -0.08
    outs
    -0.08
    æľ«
    -0.08
    POSITIVE LOGITS
    åħ¥åı£
    0.12
    æīī
    0.11
    è§Ī
    0.10
    æīĩ
    0.10
    idis
    0.10
    ä¸ĢåĽ¢
    0.10
     gateway
    0.10
     gate
    0.10
    /Gate
    0.09
    port
    0.09
    Activations Density 0.020%

    No Known Activations