© 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. 17743
    Prev
    Next
    INDEX
    Explanations

    scoop of

    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
     Battlefield
    -0.10
    DOMNode
    -0.09
     gpu
    -0.09
    ained
    -0.09
    åħ¶ä»ĸçļĦ
    -0.09
    eling
    -0.09
    ailable
    -0.09
    weit
    -0.09
    ç½¹
    -0.08
    ngine
    -0.08
    POSITIVE LOGITS
    ä¸ĢåĽ¢
    0.09
    欢åĸľ
    0.09
    .Loader
    0.08
     Abb
    0.08
    çĪ¬ä¸Ĭ
    0.08
    REV
    0.08
    許
    0.08
     amount
    0.08
    è°ĥåĬ¨
    0.08
    åłĨ积
    0.08
    Activations Density 0.023%

    No Known Activations