© 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. 32124
    Prev
    Next
    INDEX
    Explanations

    notebook and netbook

    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
    éĻĽä¸ĭ
    -0.10
    ç§ģä¸ĭ
    -0.09
    vat
    -0.09
    /Foundation
    -0.09
    éĽĦ
    -0.08
    .Formatter
    -0.08
    ä¸Ģåı¥è¯Ŀ
    -0.08
    æįĤ
    -0.08
    åĬ¡å®ŀ
    -0.08
    æ¸Ĺ
    -0.08
    POSITIVE LOGITS
    çĺ¦
    0.10
    æĽ¿ä»£
    0.10
    ãģĦãģij
    0.10
    æ´Ĺè¡£
    0.09
    ä½İå»ī
    0.09
    è¶Ĭ
    0.09
    çIJ´
    0.09
    ulia
    0.09
    æ¦ī
    0.09
    ä¹Ĵä¹ĵ
    0.08
    Activations Density 0.015%

    No Known Activations