© 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. 30278
    Prev
    Next
    INDEX
    Explanations

    here are

    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
    å±
    -0.10
    çħŀ
    -0.09
    çľ¼æ³ª
    -0.09
    éĨ®
    -0.09
    æĬµåĪ¶
    -0.09
    åľ¨åĵªéĩĮ
    -0.09
    Extras
    -0.09
    åĿ
    -0.09
    äºĨ好
    -0.09
    å°ı游æĪı
    -0.09
    POSITIVE LOGITS
     reasons
    0.10
    åĩłçĤ¹
    0.09
    大å¸Ī
    0.09
    ìłĢ
    0.09
    çIJĨçĶ±
    0.09
     some
    0.09
    åĿIJçĿĢ
    0.09
    åĩłç§į
    0.08
    ä¸Ģ个éĹ®é¢ĺ
    0.08
    å¾½
    0.08
    Activations Density 0.027%

    No Known Activations