© 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. 63533
    Prev
    Next
    INDEX
    Explanations

    (i.e

    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
    niest
    -0.10
    åijIJ
    -0.09
    avar
    -0.09
    çĿ¬
    -0.09
    åĺ¶
    -0.09
    à¸Ńาย
    -0.09
     Ấ
    -0.09
    æĬ¨
    -0.08
    çĶļèĩ³
    -0.08
    çļĦä¸ĢäºĽ
    -0.08
    POSITIVE LOGITS
    æĹ¥èµ·
    0.13
    ä¼łè¾¾
    0.09
    åı¯è§ģ
    0.09
    ernes
    0.09
    ame
    0.09
    ä¸įè¦ģ太
    0.08
    ãĥ³ãĤ°
    0.08
    ä¼łè¯´
    0.08
    åįĬå²Ľ
    0.08
    venue
    0.08
    Activations Density 0.038%

    No Known Activations