© 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. 22750
    Prev
    Next
    INDEX
    Explanations

    decisions and verdicts

    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
    åŀĤ
    -0.10
    æĮij
    -0.09
    å¼Ģå±Ģ
    -0.08
    коÑģ
    -0.08
    é¢Ħè§ģ
    -0.08
    对æĸ¹
    -0.08
     оÑĤд
    -0.08
    é«ĺä¸ŃçĶŁ
    -0.08
    esson
    -0.08
    è¯Ĭ
    -0.08
    POSITIVE LOGITS
    éĢĴç»Ļ
    0.10
    åĬŁ
    0.08
    åĪİ
    0.08
    æĸĩç«łæĿ¥æºIJ
    0.08
    ä¸Ĭç½ij
    0.08
    æŀķ头
    0.08
    Ctr
    0.08
    _RF
    0.08
    itate
    0.08
    æīĢéľĢè¦ģçļĦ
    0.08
    Activations Density 0.166%

    No Known Activations