© 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. 57516
    Prev
    Next
    INDEX
    Explanations

    quoted words begin

    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
    /misc
    -0.08
     sock
    -0.08
    _favorite
    -0.08
    éºĭ
    -0.08
     Cra
    -0.08
    æ¡¢
    -0.08
    ç½ij讯
    -0.07
    pell
    -0.07
    ä¸įæĸŃçļĦ
    -0.07
    agn
    -0.07
    POSITIVE LOGITS
    usp
    0.09
    åºķéĥ¨
    0.09
    /lab
    0.09
    é¢ľ
    0.09
    çĶ³ãģĹ
    0.09
    -flag
    0.09
    形象
    0.09
    athom
    0.09
    æĬµè¾¾
    0.09
    æľīå¿ħè¦ģ
    0.09
    Activations Density 0.033%

    No Known Activations