© 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. 48126
    Prev
    Next
    INDEX
    Explanations

    must be

    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
    æİ©
    -0.10
    åĨį说
    -0.09
    ä¸įä¸ĭ
    -0.09
    åĽ½ä¼ģ
    -0.09
    å½¹
    -0.09
    ä¸ĩåĪĨ
    -0.09
    äºī夺
    -0.08
    çĸij
    -0.08
    controlled
    -0.08
    omic
    -0.08
    POSITIVE LOGITS
    otron
    0.09
    ãģ¹ãģį
    0.09
    主è¦ģåĨħ容
    0.09
    说æľį
    0.09
    æłī
    0.08
    olas
    0.08
    æ´¹
    0.08
    _dbg
    0.08
     thá»ı
    0.08
     Trit
    0.08
    Activations Density 0.002%

    No Known Activations