© 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. 34773
    Prev
    Next
    INDEX
    Explanations

    This explains or introduces definitions

    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
    æĶ¾åѦ
    -0.11
    rades
    -0.10
    çľģéĴ±
    -0.10
    èļĢ
    -0.09
    æŀ¶åŃIJ
    -0.09
    æĹ©çĤ¹
    -0.09
    ANTI
    -0.09
    pole
    -0.09
    æ¼Ķç»ĥ
    -0.09
    æķĪåºĶ
    -0.09
    POSITIVE LOGITS
    积æŀģæĢ§
    0.08
    éĹ´çļĦ
    0.08
    æĺ¯è¦ģ
    0.08
    å¹´ä¹ĭ
    0.08
    æĪĸå¤ļ
    0.08
    èIJ½
    0.08
    orem
    0.08
    য
    0.08
     mor
    0.07
    å¥Ī
    0.07
    Activations Density 0.443%

    No Known Activations