© 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. 48476
    Prev
    Next
    INDEX
    Explanations

    statement or disclaimer

    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
    æľīéĴĪ对æĢ§
    -0.09
    第äºĮ个
    -0.09
    é«Ģ
    -0.09
    çļĦ第ä¸Ģ个
    -0.09
    vinc
    -0.08
    è´´åIJ§
    -0.08
    åĨľè´¸
    -0.08
    èģĶåIJĪä¼ļ
    -0.08
    говоÑĢ
    -0.08
    æĥ³åĬŀæ³ķ
    -0.08
    POSITIVE LOGITS
     statement
    0.11
    åħį责声æĺİ
    0.10
     statements
    0.10
    éļIJç§ģ
    0.10
    éĥijéĩį
    0.10
     Statement
    0.10
     Disclaimer
    0.09
    _statement
    0.09
    Statement
    0.09
    ä¸ĩä¸Ģ
    0.09
    Activations Density 0.085%

    No Known Activations