© 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. 35232
    Prev
    Next
    INDEX
    Explanations

    ordinals and dates

    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
    æŀ¶åŃIJ
    -0.09
    æľīå¿ħè¦ģ
    -0.09
    æ¯ı次
    -0.08
    eref
    -0.08
    æijŃ
    -0.08
     osob
    -0.08
    _PRE
    -0.08
    缴éĢļ车
    -0.08
    رس
    -0.08
    ä½ĵç³»
    -0.08
    POSITIVE LOGITS
    榻
    0.11
    大éĿ¢ç§¯
    0.10
    ä¸Ģéģĵ
    0.10
    å«Ĥ
    0.09
    åŃIJéĩĮ
    0.09
    teenth
    0.09
    falls
    0.09
    ä¸Ģ大æī¹
    0.09
    اء
    0.09
    desk
    0.09
    Activations Density 0.055%

    No Known Activations