© 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. 3227
    Prev
    Next
    INDEX
    Explanations

    design and designers

    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
    king
    -0.09
     Fu
    -0.09
    æĿ¡ä¾ĭ
    -0.09
    zel
    -0.09
    éļıæŶéļıåľ°
    -0.08
    æĢĢçĸij
    -0.08
    hog
    -0.08
    çĩ¥
    -0.08
    身影
    -0.08
    æŶéĹ´èĬĤçĤ¹
    -0.08
    POSITIVE LOGITS
     Designs
    0.13
    ãĥĩãĤ¶ãĤ¤ãĥ³
    0.13
    设计
    0.13
    è¨Ńè¨Ī
    0.12
     designing
    0.11
    design
    0.11
     designs
    0.11
    IDEO
    0.11
    /design
    0.11
    -designed
    0.10
    Activations Density 0.166%

    No Known Activations