© 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. 16524
    Prev
    Next
    INDEX
    Explanations

    join a group or become involved

    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
    çŁĽçĽ¾
    -0.09
    åīį段æŶéĹ´
    -0.08
    anium
    -0.08
    éĵ¨
    -0.08
    楼ä¸ĭ
    -0.08
    éĶ²
    -0.08
    æĵįåľº
    -0.08
    ä¸īçŃīå¥ĸ
    -0.08
    çħ¤æ°Ķ
    -0.08
    稿
    -0.08
    POSITIVE LOGITS
    æľŁåĨħ
    0.10
    vos
    0.09
    åĪĿæľŁ
    0.09
    ãģĹãģŁãĤī
    0.09
    forc
    0.09
    åijµ
    0.09
     vard
    0.08
    åħīèį£
    0.08
    æŃ£å¼ı
    0.08
    åĬłåħ¥
    0.08
    Activations Density 0.040%

    No Known Activations