© 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. 56325
    Prev
    Next
    INDEX
    Explanations

    over a range

    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
    æ·Ļ
    -0.09
    uze
    -0.09
    arus
    -0.09
     thân
    -0.08
    æ¦Ľ
    -0.08
    åħ¹
    -0.08
    å°Ĩè¿İæĿ¥
    -0.08
    俱
    -0.08
    å°ļ
    -0.08
    èĮ¨
    -0.08
    POSITIVE LOGITS
    .bootstrap
    0.10
    åIJĦ个çݯèĬĤ
    0.09
    undry
    0.09
    çĽ¸ä¼¼
    0.09
    åıĭè°Ĭ
    0.09
    åĪĨæķ£
    0.09
    åıłåĬł
    0.09
    ÑĤол
    0.09
     вÑĭÑĢажен
    0.09
    lij
    0.08
    Activations Density 0.051%

    No Known Activations