© 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. 24173
    Prev
    Next
    INDEX
    Explanations

    phrase specific

    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
    æĭĴ
    -0.10
    æįī
    -0.09
    igne
    -0.09
    åıĤä¸İèĢħ
    -0.09
    oux
    -0.09
    大éŨ
    -0.09
    ster
    -0.09
    æ°Ķæ°Ľ
    -0.09
    uela
    -0.09
    严éĩį
    -0.09
    POSITIVE LOGITS
    æīĢæľīçļĦ
    0.09
    BAT
    0.09
    åħ¨ç¨ĭ
    0.08
    ction
    0.08
    ClientId
    0.08
    ç¾
    0.08
    æĻ®
    0.07
    åĿĹ
    0.07
    转åıij
    0.07
    桦
    0.07
    Activations Density 0.008%

    No Known Activations