© 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. 47536
    Prev
    Next
    INDEX
    Explanations

    guys asking for help

    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
    ÑģÑĮ
    -0.09
    äºĨä»ĸçļĦ
    -0.09
    ãģĦãģĨ
    -0.09
    éĢļè¡Įè¯ģ
    -0.09
    饥饿
    -0.09
    ãģĭãģ¤
    -0.08
    .Companion
    -0.08
    äºĨä¸įå°ij
    -0.08
    大ä¼Ĺ
    -0.08
    elon
    -0.08
    POSITIVE LOGITS
    ðŁı»
    0.11
    amac
    0.10
    åĴª
    0.09
    ðŁı¼
    0.09
    ÅĦ
    0.08
    ðŁı½
    0.08
    è¾Ī
    0.08
    ợ
    0.08
    èIJ¼
    0.08
    ä¿©
    0.08
    Activations Density 0.014%

    No Known Activations