© 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. 5260
    Prev
    Next
    INDEX
    Explanations

    quote marks

    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
    éĤ°
    -0.10
    enty
    -0.10
    ******↵
    -0.10
    åľ¨è¿Ļæĸ¹éĿ¢
    -0.09
    гÑĢан
    -0.09
    以ä¸ĬçļĦ
    -0.09
    妯
    -0.09
    çĺª
    -0.09
    веÑĩ
    -0.09
    æĥŃ
    -0.08
    POSITIVE LOGITS
    åįģäºĮäºĶ
    0.14
    []"
    0.12
    []
    0.10
    ä¸Ģ带ä¸Ģè·¯
    0.10
    åįģåĽĽäºĶ
    0.10
    åįģä¸īäºĶ
    0.10
    ä¸įå¿ĺåĪĿå¿ĥ
    0.09
    (...)
    0.08
    ()"
    0.08
    ä¸ĢéĶ®
    0.08
    Activations Density 0.780%

    No Known Activations