© 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. 38586
    Prev
    Next
    INDEX
    Explanations

    copyright or code block separators

    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
    achel
    -0.10
    æľķ
    -0.09
    åłĩ
    -0.09
    æĻ¯å¾·éķĩ
    -0.09
    aldo
    -0.09
    éĩī
    -0.09
    严èĤĥ
    -0.08
    ä¼ĺè´¨çļĦ
    -0.08
    éħ±
    -0.08
     mixins
    -0.08
    POSITIVE LOGITS
    åī²
    0.09
    ALLE
    0.09
    çĸ¼çĹĽ
    0.09
    газ
    0.09
    èĶļ
    0.09
    丫
    0.09
    èĹķ
    0.09
    uhe
    0.09
     ÐľÐ¾
    0.09
    ordes
    0.08
    Activations Density 0.010%

    No Known Activations