© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-32B
    5. 32-RESID-BATCHTOPK-65K
    7. 29656
    Prev
    Next
    INDEX
    Explanations

    bios, os, or related technical terms

    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
    Negative Logits
    ONA
    -0.12
    éħ¬
    -0.10
    ä»ħ代表
    -0.09
    rics
    -0.09
    èIJ©
    -0.09
    ETY
    -0.09
    onas
    -0.09
    产ä¸ļåĽŃ
    -0.09
    èĴ´
    -0.09
    èįª
    -0.09
    POSITIVE LOGITS
    çĨŁæĤīçļĦ
    0.09
    æĭĨ
    0.09
    夹
    0.08
    .datab
    0.08
    plib
    0.08
    и
    0.08
    æĬ½è±¡
    0.08
    转载请
    0.08
    itura
    0.08
    责任åĪ¶
    0.08
    Activations Density 0.003%

    No Known Activations