© 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. 11200
    Prev
    Next
    INDEX
    Explanations

    display features LTE

    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
     ÐľÐ¾Ñģ
    -0.10
    åºļ
    -0.09
    å¹²èĦĨ
    -0.09
    åĮ¾
    -0.08
    gas
    -0.08
    AGED
    -0.08
    çľ¼åīįçļĦ
    -0.08
    è¿Ļéĥ¨åĪĨ
    -0.08
    Unchecked
    -0.08
     Penis
    -0.08
    POSITIVE LOGITS
    亮çĤ¹
    0.10
    åıŁ
    0.10
    æijĦå½±
    0.09
    èµĺ
    0.09
    leck
    0.08
     Carlson
    0.08
    ewise
    0.08
    èĢħãģ®
    0.08
    大å®Ĺ
    0.08
    容éĩı
    0.08
    Activations Density 0.061%

    No Known Activations