© 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. 34661
    Prev
    Next
    INDEX
    Explanations

    travel guides and advice

    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
    裳
    -0.09
    转载
    -0.09
    æŀŀ
    -0.09
    ased
    -0.09
    é²²
    -0.09
    vak
    -0.09
    çĦ¶æĺ¯
    -0.09
    asse
    -0.09
    é¢Ĩ导干éĥ¨
    -0.09
    ä½łåĸľæ¬¢
    -0.09
    POSITIVE LOGITS
    羯
    0.09
    åıĭ
    0.09
    翳
    0.08
    çļĤ
    0.08
    åľŁ
    0.08
     Backpack
    0.08
     Bret
    0.08
    èļĤ
    0.08
     Released
    0.08
    èĩ´
    0.08
    Activations Density 0.015%

    No Known Activations